LLM Pruning and Distillation in Practice: The Minitron Approach
Paper
• 2408.11796 • Published
• 58
readings
-
-
TableBench: A Comprehensive and Complex Benchmark for Table Question Answering
Paper • 2408.09174 • Published • 52 -
To Code, or Not To Code? Exploring Impact of Code in Pre-training
Paper • 2408.10914 • Published • 45 -
Open-FinLLMs: Open Multimodal Large Language Models for Financial Applications
Paper • 2408.11878 • Published • 63 -
Law of Vision Representation in MLLMs
Paper • 2408.16357 • Published • 95 -
CURLoRA: Stable LLM Continual Fine-Tuning and Catastrophic Forgetting Mitigation
Paper • 2408.14572 • Published • 8 -
SciLitLLM: How to Adapt LLMs for Scientific Literature Understanding
Paper • 2408.15545 • Published • 38 -
LongLLaVA: Scaling Multi-modal LLMs to 1000 Images Efficiently via Hybrid Architecture
Paper • 2409.02889 • Published • 54 -
LongCite: Enabling LLMs to Generate Fine-grained Citations in Long-context QA
Paper • 2409.02897 • Published • 48 -
Attention Heads of Large Language Models: A Survey
Paper • 2409.03752 • Published • 92 -
Guide-and-Rescale: Self-Guidance Mechanism for Effective Tuning-Free Real Image Editing
Paper • 2409.01322 • Published • 96 -
Towards a Unified View of Preference Learning for Large Language Models: A Survey
Paper • 2409.02795 • Published • 72 -
Paper Copilot: A Self-Evolving and Efficient LLM System for Personalized Academic Assistance
Paper • 2409.04593 • Published • 26 -
ProteinBench: A Holistic Evaluation of Protein Foundation Models
Paper • 2409.06744 • Published • 8 -
Qwen2.5-Coder Technical Report
Paper • 2409.12186 • Published • 153 -
Training Language Models to Self-Correct via Reinforcement Learning
Paper • 2409.12917 • Published • 140 -
HelloBench: Evaluating Long Text Generation Capabilities of Large Language Models
Paper • 2409.16191 • Published • 41 -
Making Text Embedders Few-Shot Learners
Paper • 2409.15700 • Published • 29 -
Instruction Following without Instruction Tuning
Paper • 2409.14254 • Published • 29 -
TPI-LLM: Serving 70B-scale LLMs Efficiently on Low-resource Edge Devices
Paper • 2410.00531 • Published • 33 -
From Code to Correctness: Closing the Last Mile of Code Generation with Hierarchical Debugging
Paper • 2410.01215 • Published • 39 -
Not All LLM Reasoners Are Created Equal
Paper • 2410.01748 • Published • 29 -
RATIONALYST: Pre-training Process-Supervision for Improving Reasoning
Paper • 2410.01044 • Published • 35 -
Training Language Models on Synthetic Edit Sequences Improves Code Synthesis
Paper • 2410.02749 • Published • 13 -
SageAttention: Accurate 8-Bit Attention for Plug-and-play Inference Acceleration
Paper • 2410.02367 • Published • 50 -
Addition is All You Need for Energy-efficient Language Models
Paper • 2410.00907 • Published • 151 -
Selective Attention Improves Transformer
Paper • 2410.02703 • Published • 25 -
Agent S: An Open Agentic Framework that Uses Computers Like a Human
Paper • 2410.08164 • Published • 26 -
Toward General Instruction-Following Alignment for Retrieval-Augmented Generation
Paper • 2410.09584 • Published • 48 -
A Unified View of Delta Parameter Editing in Post-Trained Large-Scale Models
Paper • 2410.13841 • Published • 16 -
HumanEval-V: Benchmarking High-Level Visual Reasoning with Complex Diagrams in Coding Tasks
Paper • 2410.12381 • Published • 43 -
Revealing the Barriers of Language Agents in Planning
Paper • 2410.12409 • Published • 27 -
Breaking the Memory Barrier: Near Infinite Batch Size Scaling for Contrastive Loss
Paper • 2410.17243 • Published • 92 -
Why Does the Effective Context Length of LLMs Fall Short?
Paper • 2410.18745 • Published • 17 -
Robots Pre-train Robots: Manipulation-Centric Robotic Representation from Large-Scale Robot Dataset
Paper • 2410.22325 • Published • 10 -
A Large Recurrent Action Model: xLSTM enables Fast Inference for Robotics Tasks
Paper • 2410.22391 • Published • 22 -
Both Text and Images Leaked! A Systematic Analysis of Multimodal LLM Data Contamination
Paper • 2411.03823 • Published • 49 -
Large Language Models Orchestrating Structured Reasoning Achieve Kaggle Grandmaster Level
Paper • 2411.03562 • Published • 69 -
HtmlRAG: HTML is Better Than Plain Text for Modeling Retrieved Knowledge in RAG Systems
Paper • 2411.02959 • Published • 71 -
Let the Flows Tell: Solving Graph Combinatorial Optimization Problems with GFlowNets
Paper • 2305.17010 • Published -
OpenCoder: The Open Cookbook for Top-Tier Code Large Language Models
Paper • 2411.04905 • Published • 127 -
Parameter-Efficient Fine-Tuning of Large Language Models for Unit Test Generation: An Empirical Study
Paper • 2411.02462 • Published • 10 -
Large Language Models Can Self-Improve in Long-context Reasoning
Paper • 2411.08147 • Published • 65 -
Cut Your Losses in Large-Vocabulary Language Models
Paper • 2411.09009 • Published • 49 -
ClinicalBench: Can LLMs Beat Traditional ML Models in Clinical Prediction?
Paper • 2411.06469 • Published • 17 -
SlimLM: An Efficient Small Language Model for On-Device Document Assistance
Paper • 2411.09944 • Published • 12 -
SageAttention2 Technical Report: Accurate 4 Bit Attention for Plug-and-play Inference Acceleration
Paper • 2411.10958 • Published • 57 -
Enhancing the Reasoning Ability of Multimodal Large Language Models via Mixed Preference Optimization
Paper • 2411.10442 • Published • 87 -
Hymba: A Hybrid-head Architecture for Small Language Models
Paper • 2411.13676 • Published • 47 -
Natural Language Reinforcement Learning
Paper • 2411.14251 • Published • 31 -
Cautious Optimizers: Improving Training with One Line of Code
Paper • 2411.16085 • Published • 19 -
Predicting Emergent Capabilities by Finetuning
Paper • 2411.16035 • Published • 7 -
Star Attention: Efficient LLM Inference over Long Sequences
Paper • 2411.17116 • Published • 53 -
o1-Coder: an o1 Replication for Coding
Paper • 2412.00154 • Published • 44 -
Critical Tokens Matter: Token-Level Contrastive Estimation Enhence LLM's Reasoning Capability
Paper • 2411.19943 • Published • 62 -
VisionZip: Longer is Better but Not Necessary in Vision Language Models
Paper • 2412.04467 • Published • 117 -
Code-as-Monitor: Constraint-aware Visual Programming for Reactive and Proactive Robotic Failure Detection
Paper • 2412.04455 • Published • 38 -
Personalized Multimodal Large Language Models: A Survey
Paper • 2412.02142 • Published • 13 -
Evaluating Language Models as Synthetic Data Generators
Paper • 2412.03679 • Published • 47 -
Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling
Paper • 2412.05271 • Published • 160 -
MAmmoTH-VL: Eliciting Multimodal Reasoning with Instruction Tuning at Scale
Paper • 2412.05237 • Published • 46 -
EXAONE 3.5: Series of Large Language Models for Real-world Use Cases
Paper • 2412.04862 • Published • 50 -
Moto: Latent Motion Token as the Bridging Language for Robot Manipulation
Paper • 2412.04445 • Published • 22 -
Evaluating and Aligning CodeLLMs on Human Preference
Paper • 2412.05210 • Published • 50 -
POINTS1.5: Building a Vision-Language Model towards Real World Applications
Paper • 2412.08443 • Published • 38 -
Phi-4 Technical Report
Paper • 2412.08905 • Published • 122 -
InternLM-XComposer2.5-OmniLive: A Comprehensive Multimodal System for Long-term Streaming Video and Audio Interactions
Paper • 2412.09596 • Published • 97 -
GenEx: Generating an Explorable World
Paper • 2412.09624 • Published • 98 -
TheAgentCompany: Benchmarking LLM Agents on Consequential Real World Tasks
Paper • 2412.14161 • Published • 51 -
Qwen2.5 Technical Report
Paper • 2412.15115 • Published • 377 -
LongBench v2: Towards Deeper Understanding and Reasoning on Realistic Long-context Multitasks
Paper • 2412.15204 • Published • 38 -
How to Synthesize Text Data without Model Collapse?
Paper • 2412.14689 • Published • 53 -
Offline Reinforcement Learning for LLM Multi-Step Reasoning
Paper • 2412.16145 • Published • 38 -
SCOPE: Optimizing Key-Value Cache Compression in Long-context Generation
Paper • 2412.13649 • Published • 21 -
B-STaR: Monitoring and Balancing Exploration and Exploitation in Self-Taught Reasoners
Paper • 2412.17256 • Published • 47 -
RobustFT: Robust Supervised Fine-tuning for Large Language Models under Noisy Response
Paper • 2412.14922 • Published • 88 -
Diving into Self-Evolving Training for Multimodal Reasoning
Paper • 2412.17451 • Published • 42 -
Revisiting In-Context Learning with Long Context Language Models
Paper • 2412.16926 • Published • 32 -
Outcome-Refining Process Supervision for Code Generation
Paper • 2412.15118 • Published • 19 -
DRT-o1: Optimized Deep Reasoning Translation via Long Chain-of-Thought
Paper • 2412.17498 • Published • 22 -
NILE: Internal Consistency Alignment in Large Language Models
Paper • 2412.16686 • Published • 8 -
LearnLM: Improving Gemini for Learning
Paper • 2412.16429 • Published • 22 -
PC Agent: While You Sleep, AI Works -- A Cognitive Journey into Digital World
Paper • 2412.17589 • Published • 14 -
3DGraphLLM: Combining Semantic Graphs and Large Language Models for 3D Scene Understanding
Paper • 2412.18450 • Published • 36 -
Fourier Position Embedding: Enhancing Attention's Periodic Extension for Length Generalization
Paper • 2412.17739 • Published • 41 -
ReMoE: Fully Differentiable Mixture-of-Experts with ReLU Routing
Paper • 2412.14711 • Published • 16 -
Ensembling Large Language Models with Process Reward-Guided Tree Search for Better Complex Reasoning
Paper • 2412.15797 • Published • 18 -
YuLan-Mini: An Open Data-efficient Language Model
Paper • 2412.17743 • Published • 66 -
Molar: Multimodal LLMs with Collaborative Filtering Alignment for Enhanced Sequential Recommendation
Paper • 2412.18176 • Published • 16 -
MMFactory: A Universal Solution Search Engine for Vision-Language Tasks
Paper • 2412.18072 • Published • 18 -
Explanatory Instructions: Towards Unified Vision Tasks Understanding and Zero-shot Generalization
Paper • 2412.18525 • Published • 74 -
Efficiently Serving LLM Reasoning Programs with Certaindex
Paper • 2412.20993 • Published • 36 -
HumanEval Pro and MBPP Pro: Evaluating Large Language Models on Self-invoking Code Generation
Paper • 2412.21199 • Published • 13 -
OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesis
Paper • 2412.19723 • Published • 87 -
2.5 Years in Class: A Multimodal Textbook for Vision-Language Pretraining
Paper • 2501.00958 • Published • 109 -
CodeElo: Benchmarking Competition-level Code Generation of LLMs with Human-comparable Elo Ratings
Paper • 2501.01257 • Published • 51 -
Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Models
Paper • 2501.01423 • Published • 44 -
ProgCo: Program Helps Self-Correction of Large Language Models
Paper • 2501.01264 • Published • 26 -
STAR: Spatial-Temporal Augmentation with Text-to-Video Models for Real-World Video Super-Resolution
Paper • 2501.02976 • Published • 56 -
BoostStep: Boosting mathematical capability of Large Language Models via improved single-step reasoning
Paper • 2501.03226 • Published • 43 -
Test-time Computing: from System-1 Thinking to System-2 Thinking
Paper • 2501.02497 • Published • 45 -
REINFORCE++: A Simple and Efficient Approach for Aligning Large Language Models
Paper • 2501.03262 • Published • 104 -
MotionBench: Benchmarking and Improving Fine-grained Video Motion Understanding for Vision Language Models
Paper • 2501.02955 • Published • 44 -
LLaVA-Mini: Efficient Image and Video Large Multimodal Models with One Vision Token
Paper • 2501.03895 • Published • 52 -
Cosmos World Foundation Model Platform for Physical AI
Paper • 2501.03575 • Published • 82 -
PPTAgent: Generating and Evaluating Presentations Beyond Text-to-Slides
Paper • 2501.03936 • Published • 23 -
An Empirical Study of Autoregressive Pre-training from Videos
Paper • 2501.05453 • Published • 41 -
Enhancing Human-Like Responses in Large Language Models
Paper • 2501.05032 • Published • 61 -
SWE-Fixer: Training Open-Source LLMs for Effective and Efficient GitHub Issue Resolution
Paper • 2501.05040 • Published • 15 -
LlamaV-o1: Rethinking Step-by-step Visual Reasoning in LLMs
Paper • 2501.06186 • Published • 65 -
VideoRAG: Retrieval-Augmented Generation over Video Corpus
Paper • 2501.05874 • Published • 75 -
OVO-Bench: How Far is Your Video-LLMs from Real-World Online Video Understanding?
Paper • 2501.05510 • Published • 44 -
The Lessons of Developing Process Reward Models in Mathematical Reasoning
Paper • 2501.07301 • Published • 100 -
Tensor Product Attention Is All You Need
Paper • 2501.06425 • Published • 90 -
Transformer^2: Self-adaptive LLMs
Paper • 2501.06252 • Published • 55 -
WebWalker: Benchmarking LLMs in Web Traversal
Paper • 2501.07572 • Published • 23 -
O1 Replication Journey -- Part 3: Inference-time Scaling for Medical Reasoning
Paper • 2501.06458 • Published • 31 -
Towards Best Practices for Open Datasets for LLM Training
Paper • 2501.08365 • Published • 62 -
MMDocIR: Benchmarking Multi-Modal Retrieval for Long Documents
Paper • 2501.08828 • Published • 30 -
Inference-Time Scaling for Diffusion Models beyond Scaling Denoising Steps
Paper • 2501.09732 • Published • 72 -
Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models
Paper • 2501.09686 • Published • 41 -
FAST: Efficient Action Tokenization for Vision-Language-Action Models
Paper • 2501.09747 • Published • 28 -
Evolving Deeper LLM Thinking
Paper • 2501.09891 • Published • 115 -
PaSa: An LLM Agent for Comprehensive Academic Paper Search
Paper • 2501.10120 • Published • 54 -
Agent-R: Training Language Model Agents to Reflect via Iterative Self-Training
Paper • 2501.11425 • Published • 109 -
Demons in the Detail: On Implementing Load Balancing Loss for Training Specialized Mixture-of-Expert Models
Paper • 2501.11873 • Published • 67 -
DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
Paper • 2501.12948 • Published • 440 -
Test-Time Preference Optimization: On-the-Fly Alignment via Iterative Textual Feedback
Paper • 2501.12895 • Published • 61 -
VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding
Paper • 2501.13106 • Published • 90 -
Kimi k1.5: Scaling Reinforcement Learning with LLMs
Paper • 2501.12599 • Published • 126 -
Autonomy-of-Experts Models
Paper • 2501.13074 • Published • 44 -
SRMT: Shared Memory for Multi-agent Lifelong Pathfinding
Paper • 2501.13200 • Published • 69 -
Sigma: Differential Rescaling of Query, Key and Value for Efficient Language Models
Paper • 2501.13629 • Published • 48 -
Baichuan-Omni-1.5 Technical Report
Paper • 2501.15368 • Published • 60 -
Qwen2.5-1M Technical Report
Paper • 2501.15383 • Published • 72 -
Over-Tokenized Transformer: Vocabulary is Generally Worth Scaling
Paper • 2501.16975 • Published • 32 -
Optimizing Large Language Model Training Using FP4 Quantization
Paper • 2501.17116 • Published • 36 -
SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training
Paper • 2501.17161 • Published • 124 -
Atla Selene Mini: A General Purpose Evaluation Model
Paper • 2501.17195 • Published • 35 -
Critique Fine-Tuning: Learning to Critique is More Effective than Learning to Imitate
Paper • 2501.17703 • Published • 59 -
Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs
Paper • 2501.18585 • Published • 61 -
s1: Simple test-time scaling
Paper • 2501.19393 • Published • 124 -
Reward-Guided Speculative Decoding for Efficient LLM Reasoning
Paper • 2501.19324 • Published • 39 -
GuardReasoner: Towards Reasoning-based LLM Safeguards
Paper • 2501.18492 • Published • 88 -
The Differences Between Direct Alignment Algorithms are a Blur
Paper • 2502.01237 • Published • 113 -
Process Reinforcement through Implicit Rewards
Paper • 2502.01456 • Published • 62 -
The Jumping Reasoning Curve? Tracking the Evolution of Reasoning Performance in GPT-[n] and o-[n] Models on Multimodal Puzzles
Paper • 2502.01081 • Published • 13 -
Scaling Embedding Layers in Language Models
Paper • 2502.01637 • Published • 24 -
Boosting Multimodal Reasoning with MCTS-Automated Structured Thinking
Paper • 2502.02339 • Published • 23 -
LayerTracer: Cognitive-Aligned Layered SVG Synthesis via Diffusion Transformer
Paper • 2502.01105 • Published • 21 -
Large Language Model Guided Self-Debugging Code Generation
Paper • 2502.02928 • Published • 13 -
TwinMarket: A Scalable Behavioral and Social Simulation for Financial Markets
Paper • 2502.01506 • Published • 38 -
SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model
Paper • 2502.02737 • Published • 255 -
Demystifying Long Chain-of-Thought Reasoning in LLMs
Paper • 2502.03373 • Published • 58 -
LIMO: Less is More for Reasoning
Paper • 2502.03387 • Published • 62 -
ConceptAttention: Diffusion Transformers Learn Highly Interpretable Features
Paper • 2502.04320 • Published • 36 -
Enhancing Code Generation for Low-Resource Languages: No Silver Bullet
Paper • 2501.19085 • Published • 5 -
Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling
Paper • 2502.06703 • Published • 152 -
SynthDetoxM: Modern LLMs are Few-Shot Parallel Detoxification Data Annotators
Paper • 2502.06394 • Published • 89 -
Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning
Paper • 2502.06781 • Published • 58 -
Lossless Acceleration of Large Language Models with Hierarchical Drafting based on Temporal Locality in Speculative Decoding
Paper • 2502.05609 • Published • 18 -
Show-o Turbo: Towards Accelerated Unified Multimodal Understanding and Generation
Paper • 2502.05415 • Published • 20 -
LM2: Large Memory Models
Paper • 2502.06049 • Published • 31 -
The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering
Paper • 2502.03628 • Published • 12 -
Matryoshka Quantization
Paper • 2502.06786 • Published • 32 -
History-Guided Video Diffusion
Paper • 2502.06764 • Published • 12 -
CustomVideoX: 3D Reference Attention Driven Dynamic Adaptation for Zero-Shot Customized Video Diffusion Transformers
Paper • 2502.06527 • Published • 11 -
The Curse of Depth in Large Language Models
Paper • 2502.05795 • Published • 40 -
MetaChain: A Fully-Automated and Zero-Code Framework for LLM Agents
Paper • 2502.05957 • Published • 15 -
Competitive Programming with Large Reasoning Models
Paper • 2502.06807 • Published • 69 -
CodeI/O: Condensing Reasoning Patterns via Code Input-Output Prediction
Paper • 2502.07316 • Published • 50 -
Teaching Language Models to Critique via Reinforcement Learning
Paper • 2502.03492 • Published • 24 -
Expect the Unexpected: FailSafe Long Context QA for Finance
Paper • 2502.06329 • Published • 133 -
Scaling Pre-training to One Hundred Billion Data for Vision Language Models
Paper • 2502.07617 • Published • 29 -
LLMs Can Easily Learn to Reason from Demonstrations Structure, not content, is what matters!
Paper • 2502.07374 • Published • 40 -
Retrieval-augmented Large Language Models for Financial Time Series Forecasting
Paper • 2502.05878 • Published • 40 -
Hephaestus: Improving Fundamental Agent Capabilities of Large Language Models through Continual Pre-Training
Paper • 2502.06589 • Published • 21 -
Forget What You Know about LLMs Evaluations - LLMs are Like a Chameleon
Paper • 2502.07445 • Published • 11 -
TransMLA: Multi-head Latent Attention Is All You Need
Paper • 2502.07864 • Published • 57 -
Distillation Scaling Laws
Paper • 2502.08606 • Published • 47 -
LLM Pretraining with Continuous Concepts
Paper • 2502.08524 • Published • 30 -
InfiniteHiP: Extending Language Model Context Up to 3 Million Tokens on a Single GPU
Paper • 2502.08910 • Published • 148 -
Skrr: Skip and Re-use Text Encoder Layers for Memory Efficient Text-to-Image Generation
Paper • 2502.08690 • Published • 43 -
SelfCite: Self-Supervised Alignment for Context Attribution in Large Language Models
Paper • 2502.09604 • Published • 37 -
Exploring the Potential of Encoder-free Architectures in 3D LMMs
Paper • 2502.09620 • Published • 26 -
Adapting Language-Specific LLMs to a Reasoning Model in One Day via Model Merging -- An Open Recipe
Paper • 2502.09056 • Published • 31 -
Logical Reasoning in Large Language Models: A Survey
Paper • 2502.09100 • Published • 24 -
DexTrack: Towards Generalizable Neural Tracking Control for Dexterous Manipulation from Human References
Paper • 2502.09614 • Published • 9 -
Can this Model Also Recognize Dogs? Zero-Shot Model Search from Weights
Paper • 2502.09619 • Published • 36 -
EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agents
Paper • 2502.09560 • Published • 35 -
The Stochastic Parrot on LLM's Shoulder: A Summative Assessment of Physical Concept Understanding
Paper • 2502.08946 • Published • 191 -
ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models
Paper • 2502.09696 • Published • 43 -
MM-RLHF: The Next Step Forward in Multimodal LLM Alignment
Paper • 2502.10391 • Published • 34 -
Diverse Inference and Verification for Advanced Reasoning
Paper • 2502.09955 • Published • 18 -
AdaPTS: Adapting Univariate Foundation Models to Probabilistic Multivariate Time Series Forecasting
Paper • 2502.10235 • Published • 9 -
We Can't Understand AI Using our Existing Vocabulary
Paper • 2502.07586 • Published • 11 -
FoNE: Precise Single-Token Number Embeddings via Fourier Features
Paper • 2502.09741 • Published • 15 -
Region-Adaptive Sampling for Diffusion Transformers
Paper • 2502.10389 • Published • 53 -
Large Language Diffusion Models
Paper • 2502.09992 • Published • 126 -
Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention
Paper • 2502.11089 • Published • 167 -
Learning Getting-Up Policies for Real-World Humanoid Robots
Paper • 2502.12152 • Published • 42 -
ReLearn: Unlearning via Learning for Large Language Models
Paper • 2502.11190 • Published • 30 -
SWE-Lancer: Can Frontier LLMs Earn $1 Million from Real-World Freelance Software Engineering?
Paper • 2502.12115 • Published • 46 -
HermesFlow: Seamlessly Closing the Gap in Multimodal Understanding and Generation
Paper • 2502.12148 • Published • 17 -
How Do LLMs Acquire New Knowledge? A Knowledge Circuits Perspective on Continual Pre-Training
Paper • 2502.11196 • Published • 23 -
SURGE: On the Potential of Large Language Models as General-Purpose Surrogate Code Executors
Paper • 2502.11167 • Published • 10 -
Diffusion-Sharpening: Fine-tuning Diffusion Models with Denoising Trajectory Sharpening
Paper • 2502.12146 • Published • 16 -
I Think, Therefore I Diffuse: Enabling Multimodal In-Context Reasoning in Diffusion Models
Paper • 2502.10458 • Published • 38 -
Intuitive physics understanding emerges from self-supervised pretraining on natural videos
Paper • 2502.11831 • Published • 20 -
CRANE: Reasoning with constrained LLM generation
Paper • 2502.09061 • Published • 21 -
Memory, Benchmark & Robots: A Benchmark for Solving Complex Tasks with Reinforcement Learning
Paper • 2502.10550 • Published • 8 -
MagicArticulate: Make Your 3D Models Articulation-Ready
Paper • 2502.12135 • Published • 8 -
Soundwave: Less is More for Speech-Text Alignment in LLMs
Paper • 2502.12900 • Published • 86 -
SoFar: Language-Grounded Orientation Bridges Spatial Reasoning and Object Manipulation
Paper • 2502.13143 • Published • 31 -
Multimodal Mamba: Decoder-only Multimodal State Space Model via Quadratic to Linear Distillation
Paper • 2502.13145 • Published • 38 -
FLAG-Trader: Fusion LLM-Agent with Gradient-based Reinforcement Learning for Financial Trading
Paper • 2502.11433 • Published • 36 -
You Do Not Fully Utilize Transformer's Representation Capacity
Paper • 2502.09245 • Published • 37 -
Magma: A Foundation Model for Multimodal AI Agents
Paper • 2502.13130 • Published • 58 -
Revisiting the Test-Time Scaling of o1-like Models: Do they Truly Possess Test-Time Scaling Capabilities?
Paper • 2502.12215 • Published • 16 -
Qwen2.5-VL Technical Report
Paper • 2502.13923 • Published • 214 -
SongGen: A Single Stage Auto-regressive Transformer for Text-to-Song Generation
Paper • 2502.13128 • Published • 41 -
Craw4LLM: Efficient Web Crawling for LLM Pretraining
Paper • 2502.13347 • Published • 30 -
Small Models Struggle to Learn from Strong Reasoners
Paper • 2502.12143 • Published • 39 -
Is That Your Final Answer? Test-Time Scaling Improves Selective Question Answering
Paper • 2502.13962 • Published • 28 -
AdaptiveStep: Automatically Dividing Reasoning Step through Model Confidence
Paper • 2502.13943 • Published • 8 -
SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features
Paper • 2502.14786 • Published • 158 -
S*: Test Time Scaling for Code Generation
Paper • 2502.14382 • Published • 63 -
How Much Knowledge Can You Pack into a LoRA Adapter without Harming LLM?
Paper • 2502.14502 • Published • 91 -
Does Time Have Its Place? Temporal Heads: Where Language Models Recall Time-specific Information
Paper • 2502.14258 • Published • 26 -
VLM^2-Bench: A Closer Look at How Well VLMs Implicitly Link Explicit Matching Visual Cues
Paper • 2502.12084 • Published • 35 -
SurveyX: Academic Survey Automation via Large Language Models
Paper • 2502.14776 • Published • 100 -
Make LoRA Great Again: Boosting LoRA with Adaptive Singular Values and Mixture-of-Experts Optimization Alignment
Paper • 2502.16894 • Published • 32 -
DICEPTION: A Generalist Diffusion Model for Visual Perceptual Tasks
Paper • 2502.17157 • Published • 52 -
VideoGrain: Modulating Space-Time Attention for Multi-grained Video Editing
Paper • 2502.17258 • Published • 79 -
SpargeAttn: Accurate Sparse Attention Accelerating Any Model Inference
Paper • 2502.18137 • Published • 60 -
Kanana: Compute-efficient Bilingual Language Models
Paper • 2502.18934 • Published • 65 -
Self-rewarding correction for mathematical reasoning
Paper • 2502.19613 • Published • 82 -
Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs
Paper • 2503.01743 • Published • 89 -
Visual-RFT: Visual Reinforcement Fine-Tuning
Paper • 2503.01785 • Published • 86 -
CodeArena: A Collective Evaluation Platform for LLM Code Generation
Paper • 2503.01295 • Published • 8 -
Babel: Open Multilingual Large Language Models Serving Over 90% of Global Speakers
Paper • 2503.00865 • Published • 64 -
ABC: Achieving Better Control of Multimodal Embeddings using VLMs
Paper • 2503.00329 • Published • 20 -
Token-Efficient Long Video Understanding for Multimodal LLMs
Paper • 2503.04130 • Published • 96 -
EgoLife: Towards Egocentric Life Assistant
Paper • 2503.03803 • Published • 46 -
START: Self-taught Reasoner with Tools
Paper • 2503.04625 • Published • 113 -
LLMVoX: Autoregressive Streaming Text-to-Speech Model for Any LLM
Paper • 2503.04724 • Published • 72 -
Unified Reward Model for Multimodal Understanding and Generation
Paper • 2503.05236 • Published • 123 -
Sketch-of-Thought: Efficient LLM Reasoning with Adaptive Cognitive-Inspired Sketching
Paper • 2503.05179 • Published • 46 -
Forgetting Transformer: Softmax Attention with a Forget Gate
Paper • 2503.02130 • Published • 32 -
BEHAVIOR Robot Suite: Streamlining Real-World Whole-Body Manipulation for Everyday Household Activities
Paper • 2503.05652 • Published • 11 -
LoRACode: LoRA Adapters for Code Embeddings
Paper • 2503.05315 • Published • 13 -
Feature-Level Insights into Artificial Text Detection with Sparse Autoencoders
Paper • 2503.03601 • Published • 232 -
FEA-Bench: A Benchmark for Evaluating Repository-Level Code Generation for Feature Implementation
Paper • 2503.06680 • Published • 20 -
LMM-R1: Empowering 3B LMMs with Strong Reasoning Abilities Through Two-Stage Rule-Based RL
Paper • 2503.07536 • Published • 88 -
SegAgent: Exploring Pixel Understanding Capabilities in MLLMs by Imitating Human Annotator Trajectories
Paper • 2503.08625 • Published • 27 -
Gemini Embedding: Generalizable Embeddings from Gemini
Paper • 2503.07891 • Published • 45 -
Implicit Reasoning in Transformers is Reasoning through Shortcuts
Paper • 2503.07604 • Published • 23 -
Optimizing Test-Time Compute via Meta Reinforcement Fine-Tuning
Paper • 2503.07572 • Published • 48 -
AnyMoLe: Any Character Motion In-betweening Leveraging Video Diffusion Models
Paper • 2503.08417 • Published • 8 -
Mixture of Experts Made Intrinsically Interpretable
Paper • 2503.07639 • Published • 10 -
AI-native Memory 2.0: Second Me
Paper • 2503.08102 • Published • 13 -
TPDiff: Temporal Pyramid Video Diffusion Model
Paper • 2503.09566 • Published • 45 -
Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models
Paper • 2503.09573 • Published • 76 -
GTR: Guided Thought Reinforcement Prevents Thought Collapse in RL-based VLM Agent Training
Paper • 2503.08525 • Published • 17 -
More Documents, Same Length: Isolating the Challenge of Multiple Documents in RAG
Paper • 2503.04388 • Published • 17 -
Quantizing Large Language Models for Code Generation: A Differentiated Replication
Paper • 2503.07103 • Published • 8 -
Adversarial Data Collection: Human-Collaborative Perturbations for Efficient and Robust Robotic Imitation Learning
Paper • 2503.11646 • Published • 34 -
Cosmos-Transfer1: Conditional World Generation with Adaptive Multimodal Control
Paper • 2503.14492 • Published • 20 -
φ-Decoding: Adaptive Foresight Sampling for Balanced Inference-Time Exploration and Exploitation
Paper • 2503.13288 • Published • 51 -
Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models
Paper • 2503.16419 • Published • 77 -
DiffMoE: Dynamic Token Selection for Scalable Diffusion Transformers
Paper • 2503.14487 • Published • 28 -
Cosmos-Reason1: From Physical Common Sense To Embodied Reasoning
Paper • 2503.15558 • Published • 50 -
Expert Race: A Flexible Routing Strategy for Scaling Diffusion Transformer with Mixture of Experts
Paper • 2503.16057 • Published • 14 -
Tokenize Image as a Set
Paper • 2503.16425 • Published • 16 -
BigO(Bench) -- Can LLMs Generate Code with Controlled Time and Space Complexity?
Paper • 2503.15242 • Published • 10 -
JARVIS-VLA: Post-Training Large-Scale Vision Language Models to Play Visual Games with Keyboards and Mouse
Paper • 2503.16365 • Published • 41 -
Reinforcement Learning for Reasoning in Small LLMs: What Works and What Doesn't
Paper • 2503.16219 • Published • 52 -
I Have Covered All the Bases Here: Interpreting Reasoning Features in Large Language Models via Sparse Autoencoders
Paper • 2503.18878 • Published • 119 -
Video-T1: Test-Time Scaling for Video Generation
Paper • 2503.18942 • Published • 90 -
AlphaSpace: Enabling Robotic Actions through Semantic Tokenization and Symbolic Reasoning
Paper • 2503.18769 • Published • 11 -
CoMP: Continual Multimodal Pre-training for Vision Foundation Models
Paper • 2503.18931 • Published • 30 -
Long-Context Autoregressive Video Modeling with Next-Frame Prediction
Paper • 2503.19325 • Published • 73 -
Exploring Hallucination of Large Multimodal Models in Video Understanding: Benchmark, Analysis and Mitigation
Paper • 2503.19622 • Published • 31 -
Scaling Vision Pre-Training to 4K Resolution
Paper • 2503.19903 • Published • 41 -
UI-R1: Enhancing Action Prediction of GUI Agents by Reinforcement Learning
Paper • 2503.21620 • Published • 62 -
Large Language Model Agent: A Survey on Methodology, Applications and Challenges
Paper • 2503.21460 • Published • 83 -
ReaRAG: Knowledge-guided Reasoning Enhances Factuality of Large Reasoning Models with Iterative Retrieval Augmented Generation
Paper • 2503.21729 • Published • 29 -
Embodied-Reasoner: Synergizing Visual Search, Reasoning, and Action for Embodied Interactive Tasks
Paper • 2503.21696 • Published • 23 -
Think Before Recommend: Unleashing the Latent Reasoning Power for Sequential Recommendation
Paper • 2503.22675 • Published • 36 -
Segment Any Motion in Videos
Paper • 2503.22268 • Published • 19 -
Your ViT is Secretly an Image Segmentation Model
Paper • 2503.19108 • Published • 25 -
What, How, Where, and How Well? A Survey on Test-Time Scaling in Large Language Models
Paper • 2503.24235 • Published • 54 -
Any2Caption:Interpreting Any Condition to Caption for Controllable Video Generation
Paper • 2503.24379 • Published • 76 -
Exploring the Effect of Reinforcement Learning on Video Understanding: Insights from SEED-Bench-R1
Paper • 2503.24376 • Published • 38 -
Z1: Efficient Test-time Scaling with Code
Paper • 2504.00810 • Published • 26 -
Multi-Token Attention
Paper • 2504.00927 • Published • 56 -
Scaling Language-Free Visual Representation Learning
Paper • 2504.01017 • Published • 32 -
Command A: An Enterprise-Ready Large Language Model
Paper • 2504.00698 • Published • 29 -
MergeVQ: A Unified Framework for Visual Generation and Representation with Disentangled Token Merging and Quantization
Paper • 2504.00999 • Published • 95 -
ScholarCopilot: Training Large Language Models for Academic Writing with Accurate Citations
Paper • 2504.00824 • Published • 43 -
PaperBench: Evaluating AI's Ability to Replicate AI Research
Paper • 2504.01848 • Published • 37 -
Articulated Kinematics Distillation from Video Diffusion Models
Paper • 2504.01204 • Published • 23 -
Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems
Paper • 2504.01990 • Published • 303 -
ZClip: Adaptive Spike Mitigation for LLM Pre-Training
Paper • 2504.02507 • Published • 88 -
SmolVLM: Redefining small and efficient multimodal models
Paper • 2504.05299 • Published • 205 -
URECA: Unique Region Caption Anything
Paper • 2504.05305 • Published • 35 -
DDT: Decoupled Diffusion Transformer
Paper • 2504.05741 • Published • 77 -
RobustDexGrasp: Robust Dexterous Grasping of General Objects from Single-view Perception
Paper • 2504.05287 • Published • 6 -
Kimi-VL Technical Report
Paper • 2504.07491 • Published • 137 -
DeepSeek-R1 Thoughtology: Let's <think> about LLM Reasoning
Paper • 2504.07128 • Published • 87 -
Seaweed-7B: Cost-Effective Training of Video Generation Foundation Model
Paper • 2504.08685 • Published • 130 -
GigaTok: Scaling Visual Tokenizers to 3 Billion Parameters for Autoregressive Image Generation
Paper • 2504.08736 • Published • 46 -
MineWorld: a Real-Time and Open-Source Interactive World Model on Minecraft
Paper • 2504.08388 • Published • 42 -
PixelFlow: Pixel-Space Generative Models with Flow
Paper • 2504.07963 • Published • 18 -
Do PhD-level LLMs Truly Grasp Elementary Addition? Probing Rule Learning vs. Memorization in Large Language Models
Paper • 2504.05262 • Published • 11 -
InteractVLM: 3D Interaction Reasoning from 2D Foundational Models
Paper • 2504.05303 • Published • 5 -
InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models
Paper • 2504.10479 • Published • 306 -
PRIMA.CPP: Speeding Up 70B-Scale LLM Inference on Low-Resource Everyday Home Clusters
Paper • 2504.08791 • Published • 139 -
FUSION: Fully Integration of Vision-Language Representations for Deep Cross-Modal Understanding
Paper • 2504.09925 • Published • 39 -
ColorBench: Can VLMs See and Understand the Colorful World? A Comprehensive Benchmark for Color Perception, Reasoning, and Robustness
Paper • 2504.10514 • Published • 48 -
Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?
Paper • 2504.13837 • Published • 139 -
Learning to Reason under Off-Policy Guidance
Paper • 2504.14945 • Published • 88 -
Eagle 2.5: Boosting Long-Context Post-Training for Frontier Vision-Language Models
Paper • 2504.15271 • Published • 67 -
ToolRL: Reward is All Tool Learning Needs
Paper • 2504.13958 • Published • 49 -
Kuwain 1.5B: An Arabic SLM via Language Injection
Paper • 2504.15120 • Published • 121 -
Describe Anything: Detailed Localized Image and Video Captioning
Paper • 2504.16072 • Published • 64 -
Breaking the Modality Barrier: Universal Embedding Learning with Multimodal LLMs
Paper • 2504.17432 • Published • 40 -
RoboVerse: Towards a Unified Platform, Dataset and Benchmark for Scalable and Generalizable Robot Learning
Paper • 2504.18904 • Published • 9 -
Voila: Voice-Language Foundation Models for Real-Time Autonomous Interaction and Voice Role-Play
Paper • 2505.02707 • Published • 85 -
Vision-Language-Action Models: Concepts, Progress, Applications and Challenges
Paper • 2505.04769 • Published • 10 -
Bielik v3 Small: Technical Report
Paper • 2505.02550 • Published • 68 -
Bielik 11B v2 Technical Report
Paper • 2505.02410 • Published • 54 -
UniVLA: Learning to Act Anywhere with Task-centric Latent Actions
Paper • 2505.06111 • Published • 25 -
Seed1.5-VL Technical Report
Paper • 2505.07062 • Published • 155 -
DeCLIP: Decoupled Learning for Open-Vocabulary Dense Perception
Paper • 2505.04410 • Published • 44 -
BLIP3-o: A Family of Fully Open Unified Multimodal Models-Architecture, Training and Dataset
Paper • 2505.09568 • Published • 99 -
Beyond 'Aha!': Toward Systematic Meta-Abilities Alignment in Large Reasoning Models
Paper • 2505.10554 • Published • 120 -
EnerVerse-AC: Envisioning Embodied Environments with Action Condition
Paper • 2505.09723 • Published • 23 -
EWMBench: Evaluating Scene, Motion, and Semantic Quality in Embodied World Models
Paper • 2505.09694 • Published • 20 -
Qwen3 Technical Report
Paper • 2505.09388 • Published • 335 -
Chain-of-Model Learning for Language Model
Paper • 2505.11820 • Published • 121 -
AdaptThink: Reasoning Models Can Learn When to Think
Paper • 2505.13417 • Published • 83 -
Delta Attention: Fast and Accurate Sparse Attention Inference by Delta Correction
Paper • 2505.11254 • Published • 48 -
Faster Video Diffusion with Trainable Sparse Attention
Paper • 2505.13389 • Published • 38 -
Model Merging in Pre-training of Large Language Models
Paper • 2505.12082 • Published • 40 -
Emerging Properties in Unified Multimodal Pretraining
Paper • 2505.14683 • Published • 133 -
SageAttention3: Microscaling FP4 Attention for Inference and An Exploration of 8-Bit Training
Paper • 2505.11594 • Published • 75 -
Scaling Law for Quantization-Aware Training
Paper • 2505.14302 • Published • 76 -
MMaDA: Multimodal Large Diffusion Language Models
Paper • 2505.15809 • Published • 98 -
Diffusion vs. Autoregressive Language Models: A Text Embedding Perspective
Paper • 2505.15045 • Published • 55 -
This Time is Different: An Observability Perspective on Time Series Foundation Models
Paper • 2505.14766 • Published • 40 -
NovelSeek: When Agent Becomes the Scientist -- Building Closed-Loop System from Hypothesis to Verification
Paper • 2505.16938 • Published • 121 -
Tool-Star: Empowering LLM-Brained Multi-Tool Reasoner via Reinforcement Learning
Paper • 2505.16410 • Published • 58 -
LLaDA-V: Large Language Diffusion Models with Visual Instruction Tuning
Paper • 2505.16933 • Published • 34 -
How Do Large Vision-Language Models See Text in Image? Unveiling the Distinctive Role of OCR Heads
Paper • 2505.15865 • Published • 5 -
One RL to See Them All: Visual Triple Unified Reinforcement Learning
Paper • 2505.18129 • Published • 62 -
Model Already Knows the Best Noise: Bayesian Active Noise Selection via Attention in Video Diffusion Model
Paper • 2505.17561 • Published • 31 -
Shifting AI Efficiency From Model-Centric to Data-Centric Compression
Paper • 2505.19147 • Published • 145 -
Mutarjim: Advancing Bidirectional Arabic-English Translation with a Small Language Model
Paper • 2505.17894 • Published • 220 -
Embodied Agents Meet Personalization: Exploring Memory Utilization for Personalized Assistance
Paper • 2505.16348 • Published • 52 -
ARM: Adaptive Reasoning Model
Paper • 2505.20258 • Published • 45 -
Vibe Coding vs. Agentic Coding: Fundamentals and Practical Implications of Agentic AI
Paper • 2505.19443 • Published • 15 -
Paper2Poster: Towards Multimodal Poster Automation from Scientific Papers
Paper • 2505.21497 • Published • 109 -
Exploring the Latent Capacity of LLMs for One-Step Text Generation
Paper • 2505.21189 • Published • 61 -
ATLAS: Learning to Optimally Memorize the Context at Test Time
Paper • 2505.23735 • Published • 23 -
Robot-R1: Reinforcement Learning for Enhanced Embodied Reasoning in Robotics
Paper • 2506.00070 • Published • 29 -
MiMo-VL Technical Report
Paper • 2506.03569 • Published • 80 -
CASS: Nvidia to AMD Transpilation with Data, Models, and Benchmark
Paper • 2505.16968 • Published • 40 -
AmbiK: Dataset of Ambiguous Tasks in Kitchen Environment
Paper • 2506.04089 • Published • 47 -
VisCoder: Fine-Tuning LLMs for Executable Python Visualization Code Generation
Paper • 2506.03930 • Published • 26 -
Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models
Paper • 2506.05176 • Published • 79 -
The Common Pile v0.1: An 8TB Dataset of Public Domain and Openly Licensed Text
Paper • 2506.05209 • Published • 60 -
RoboRefer: Towards Spatial Referring with Reasoning in Vision-Language Models for Robotics
Paper • 2506.04308 • Published • 43 -
Reinforcement Pre-Training
Paper • 2506.08007 • Published • 263 -
MiniCPM4: Ultra-Efficient LLMs on End Devices
Paper • 2506.07900 • Published • 95 -
SpatialLM: Training Large Language Models for Structured Indoor Modeling
Paper • 2506.07491 • Published • 50 -
Astra: Toward General-Purpose Mobile Robots via Hierarchical Multimodal Learning
Paper • 2506.06205 • Published • 30 -
PlayerOne: Egocentric World Simulator
Paper • 2506.09995 • Published • 34 -
Auto-Regressive vs Flow-Matching: a Comparative Study of Modeling Paradigms for Text-to-Music Generation
Paper • 2506.08570 • Published • 33 -
The Diffusion Duality
Paper • 2506.10892 • Published • 37 -
MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention
Paper • 2506.13585 • Published • 273 -
Unified Vision-Language-Action Model
Paper • 2506.19850 • Published • 27 -
WorldVLA: Towards Autoregressive Action World Model
Paper • 2506.21539 • Published • 40 -
Where to find Grokking in LLM Pretraining? Monitor Memorization-to-Generalization without Test
Paper • 2506.21551 • Published • 28 -
Ark: An Open-source Python-based Framework for Robot Learning
Paper • 2506.21628 • Published • 16 -
Kwai Keye-VL Technical Report
Paper • 2507.01949 • Published • 131 -
Depth Anything at Any Condition
Paper • 2507.01634 • Published • 49 -
A Survey on Vision-Language-Action Models: An Action Tokenization Perspective
Paper • 2507.01925 • Published • 39 -
T-LoRA: Single Image Diffusion Model Customization Without Overfitting
Paper • 2507.05964 • Published • 120 -
PhysX: Physical-Grounded 3D Asset Generation
Paper • 2507.12465 • Published • 44 -
A Survey of Context Engineering for Large Language Models
Paper • 2507.13334 • Published • 261 -
VisionThink: Smart and Efficient Vision Language Model via Reinforcement Learning
Paper • 2507.13348 • Published • 79 -
Set Block Decoding is a Language Model Inference Accelerator
Paper • 2509.04185 • Published • 54 -
Why Language Models Hallucinate
Paper • 2509.04664 • Published • 196 -
VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model
Paper • 2509.09372 • Published • 246 -
SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning
Paper • 2509.09674 • Published • 80 -
FLOWER: Democratizing Generalist Robot Policies with Efficient Vision-Language-Action Flow Policies
Paper • 2509.04996 • Published • 15 -
QuantAgent: Price-Driven Multi-Agent LLMs for High-Frequency Trading
Paper • 2509.09995 • Published • 16 -
ByteWrist: A Parallel Robotic Wrist Enabling Flexible and Anthropomorphic Motion for Confined Spaces
Paper • 2509.18084 • Published • 13 -
Residual Off-Policy RL for Finetuning Behavior Cloning Policies
Paper • 2509.19301 • Published • 19 -
DA^2: Depth Anything in Any Direction
Paper • 2509.26618 • Published • 26 -
LongCodeZip: Compress Long Context for Code Language Models
Paper • 2510.00446 • Published • 107 -
VLA-R1: Enhancing Reasoning in Vision-Language-Action Models
Paper • 2510.01623 • Published • 12 -
ExGRPO: Learning to Reason from Experience
Paper • 2510.02245 • Published • 80 -
Paper2Video: Automatic Video Generation from Scientific Papers
Paper • 2510.05096 • Published • 119 -
MM-HELIX: Boosting Multimodal Long-Chain Reflective Reasoning with Holistic Platform and Adaptive Hybrid Policy Optimization
Paper • 2510.08540 • Published • 109 -
Hybrid Reinforcement: When Reward Is Sparse, It's Better to Be Dense
Paper • 2510.07242 • Published • 30 -
Reinforcing Diffusion Models by Direct Group Preference Optimization
Paper • 2510.08425 • Published • 12 -
DexNDM: Closing the Reality Gap for Dexterous In-Hand Rotation via Joint-Wise Neural Dynamics Model
Paper • 2510.08556 • Published • 7 -
R2RGEN: Real-to-Real 3D Data Generation for Spatially Generalized Manipulation
Paper • 2510.08547 • Published • 5 -
D2E: Scaling Vision-Action Pretraining on Desktop Data for Transfer to Embodied AI
Paper • 2510.05684 • Published • 143 -
Don't Waste Mistakes: Leveraging Negative RL-Groups via Confidence Reweighting
Paper • 2510.08696 • Published • 15 -
Robot Learning: A Tutorial
Paper • 2510.12403 • Published • 123 -
LIBERO-Plus: In-depth Robustness Analysis of Vision-Language-Action Models
Paper • 2510.13626 • Published • 46 -
ParallelBench: Understanding the Trade-offs of Parallel Decoding in Diffusion LLMs
Paper • 2510.04767 • Published • 28 -
The Art of Scaling Reinforcement Learning Compute for LLMs
Paper • 2510.13786 • Published • 32 -
LaSeR: Reinforcement Learning with Last-Token Self-Rewarding
Paper • 2510.14943 • Published • 40 -
VLA^2: Empowering Vision-Language-Action Models with an Agentic Framework for Unseen Concept Manipulation
Paper • 2510.14902 • Published • 17 -
VLA-0: Building State-of-the-Art VLAs with Zero Modification
Paper • 2510.13054 • Published • 16 -
SimKO: Simple Pass@K Policy Optimization
Paper • 2510.14807 • Published • 11 -
pi-Flow: Policy-Based Few-Step Generation via Imitation Distillation
Paper • 2510.14974 • Published • 10 -
AnyUp: Universal Feature Upsampling
Paper • 2510.12764 • Published • 12 -
Scaling Instruction-Based Video Editing with a High-Quality Synthetic Dataset
Paper • 2510.15742 • Published • 51 -
LightsOut: Diffusion-based Outpainting for Enhanced Lens Flare Removal
Paper • 2510.15868 • Published • 27 -
RL makes MLLMs see better than SFT
Paper • 2510.16333 • Published • 49 -
Chronos-2: From Univariate to Universal Forecasting
Paper • 2510.15821 • Published • 22 -
Visual Autoregressive Models Beat Diffusion Models on Inference Time Scaling
Paper • 2510.16751 • Published • 21 -
RoboOmni: Proactive Robot Manipulation in Omni-modal Context
Paper • 2510.23763 • Published • 56 -
Exploring Conditions for Diffusion models in Robotic Control
Paper • 2510.15510 • Published • 40 -
π_RL: Online RL Fine-tuning for Flow-based Vision-Language-Action Models
Paper • 2510.25889 • Published • 66 -
World Simulation with Video Foundation Models for Physical AI
Paper • 2511.00062 • Published • 44 -
Unified Diffusion VLA: Vision-Language-Action Model via Joint Discrete Denoising Diffusion Process
Paper • 2511.01718 • Published • 7 -
Don't Blind Your VLA: Aligning Visual Representations for OOD Generalization
Paper • 2510.25616 • Published • 105 -
Robot Learning from a Physical World Model
Paper • 2511.07416 • Published • 32 -
Depth Anything 3: Recovering the Visual Space from Any Views
Paper • 2511.10647 • Published • 99 -
SRPO: Self-Referential Policy Optimization for Vision-Language-Action Models
Paper • 2511.15605 • Published • 24 -
RynnVLA-002: A Unified Vision-Language-Action and World Model
Paper • 2511.17502 • Published • 28 -
MobileVLA-R1: Reinforcing Vision-Language-Action for Mobile Robots
Paper • 2511.17889 • Published • 5 -
ENACT: Evaluating Embodied Cognition with World Modeling of Egocentric Interaction
Paper • 2511.20937 • Published • 16 -
Qwen3-VL Technical Report
Paper • 2511.21631 • Published • 158 -
Steering Vision-Language-Action Models as Anti-Exploration: A Test-Time Scaling Approach
Paper • 2512.02834 • Published • 41 -
Flowing Backwards: Improving Normalizing Flows via Reverse Representation Alignment
Paper • 2511.22345 • Published • 13 -
VideoVLA: Video Generators Can Be Generalizable Robot Manipulators
Paper • 2512.06963 • Published • 4 -
HiF-VLA: Hindsight, Insight and Foresight through Motion Representation for Vision-Language-Action Models
Paper • 2512.09928 • Published • 14 -
LEO-RobotAgent: A General-purpose Robotic Agent for Language-driven Embodied Operator
Paper • 2512.10605 • Published • 7 -
Task adaptation of Vision-Language-Action model: 1st Place Solution for the 2025 BEHAVIOR Challenge
Paper • 2512.06951 • Published • 4 -
Memory in the Age of AI Agents
Paper • 2512.13564 • Published • 151 -
Openpi Comet: Competition Solution For 2025 BEHAVIOR Challenge
Paper • 2512.10071 • Published • 18 -
VLSA: Vision-Language-Action Models with Plug-and-Play Safety Constraint Layer
Paper • 2512.11891 • Published • 10 -
Learning Robot Manipulation from Audio World Models
Paper • 2512.08405 • Published • 2 -
LoGoPlanner: Localization Grounded Navigation Policy with Metric-aware Visual Geometry
Paper • 2512.19629 • Published • 26 -
SOP: A Scalable Online Post-Training System for Vision-Language-Action Models
Paper • 2601.03044 • Published • 28 -
E-GRPO: High Entropy Steps Drive Effective Reinforcement Learning for Flow Models
Paper • 2601.00423 • Published • 11 -
AT^2PO: Agentic Turn-based Policy Optimization via Tree Search
Paper • 2601.04767 • Published • 28 -
Beyond Binary Preference: Aligning Diffusion Models to Fine-grained Criteria by Decoupling Attributes
Paper • 2601.04300 • Published • 3 -
GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization
Paper • 2601.05242 • Published • 228 -
RoboVIP: Multi-View Video Generation with Visual Identity Prompting Augments Robot Manipulation
Paper • 2601.05241 • Published • 24 -
Solar Open Technical Report
Paper • 2601.07022 • Published • 65 -
Ministral 3
Paper • 2601.08584 • Published • 54 -
ShowUI-π: Flow-based Generative Models as GUI Dexterous Hands
Paper • 2512.24965 • Published • 42 -
FlowAct-R1: Towards Interactive Humanoid Video Generation
Paper • 2601.10103 • Published • 74 -
Action100M: A Large-scale Video Action Dataset
Paper • 2601.10592 • Published • 29 -
ACoT-VLA: Action Chain-of-Thought for Vision-Language-Action Models
Paper • 2601.11404 • Published • 26 -
FrankenMotion: Part-level Human Motion Generation and Composition
Paper • 2601.10909 • Published • 18 -
Being-H0.5: Scaling Human-Centric Robot Learning for Cross-Embodiment Generalization
Paper • 2601.12993 • Published • 75 -
BayesianVLA: Bayesian Decomposition of Vision Language Action Models via Latent Action Queries
Paper • 2601.15197 • Published • 54 -
Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and Planning
Paper • 2601.16163 • Published • 14 -
TwinBrainVLA: Unleashing the Potential of Generalist VLMs for Embodied Tasks via Asymmetric Mixture-of-Transformers
Paper • 2601.14133 • Published • 61 -
A Pragmatic VLA Foundation Model
Paper • 2601.18692 • Published • 47 -
Advancing Open-source World Models
Paper • 2601.20540 • Published • 128 -
DynamicVLA: A Vision-Language-Action Model for Dynamic Object Manipulation
Paper • 2601.22153 • Published • 71 -
Beyond Imitation: Reinforcement Learning for Active Latent Planning
Paper • 2601.21598 • Published • 9 -
DenseGRPO: From Sparse to Dense Reward for Flow Matching Model Alignment
Paper • 2601.20218 • Published • 15 -
Green-VLA: Staged Vision-Language-Action Model for Generalist Robots
Paper • 2602.00919 • Published • 305 -
SoMA: A Real-to-Sim Neural Simulator for Robotic Soft-body Manipulation
Paper • 2602.02402 • Published • 32 -
VLS: Steering Pretrained Robot Policies via Vision-Language Models
Paper • 2602.03973 • Published • 22 -
VLA-JEPA: Enhancing Vision-Language-Action Model with Latent World Model
Paper • 2602.10098 • Published • 18 -
PhyCritic: Multimodal Critic Models for Physical AI
Paper • 2602.11124 • Published • 52 -
GigaBrain-0.5M*: a VLA That Learns From World Model-Based Reinforcement Learning
Paper • 2602.12099 • Published • 57 -
χ_{0}: Resource-Aware Robust Manipulation via Taming Distributional Inconsistencies
Paper • 2602.09021 • Published • 25 -
RISE: Self-Improving Robot Policy with Compositional World Model
Paper • 2602.11075 • Published • 30 -
EgoHumanoid: Unlocking In-the-Wild Loco-Manipulation with Robot-Free Egocentric Demonstration
Paper • 2602.10106 • Published • 21 -
Learning Humanoid End-Effector Control for Open-Vocabulary Visual Loco-Manipulation
Paper • 2602.16705 • Published • 26 -
RynnBrain: Open Embodied Foundation Models
Paper • 2602.14979 • Published • 42 -
World Action Models are Zero-shot Policies
Paper • 2602.15922 • Published • 11 -
TactAlign: Human-to-Robot Policy Transfer via Tactile Alignment
Paper • 2602.13579 • Published • 10 -
QuantVLA: Scale-Calibrated Post-Training Quantization for Vision-Language-Action Models
Paper • 2602.20309 • Published • 10