Command Palette
Search for a command to run...
Papers
Daily updated cutting-edge AI research papers to help you keep up with the latest AI trends
papers

OceanGym: A Benchmark Environment for Underwater Embodied Agents

TruthRL: Incentivizing Truthful LLMs via Reinforcement Learning




























Winning the Pruning Gamble: A Unified Approach to Joint Sample and Token Pruning for Efficient Supervised Fine-Tuning
The Dragon Hatchling: The Missing Link between the Transformer and Models of the Brain
Vision-Zero: Scalable VLM Self-Improvement via Strategic Gamified Self-Play
MCPMark: A Benchmark for Stress-Testing Realistic and Comprehensive MCP Use
Random Policy Valuation is Enough for LLM Reasoning with Verifiable Rewards
Democratizing AI scientists using ToolUniverse
When Does Reasoning Matter? A Controlled Study of Reasoning's Contribution to Model Performance
Multiplayer Nash Preference Optimization
StableToken: A Noise-Robust Semantic Speech Tokenizer for Resilient SpeechLLMs
SLA: Beyond Sparsity in Diffusion Transformers via Fine-Tunable Sparse-Linear Attention
SimpleFold: Folding Proteins is Simpler than You Think
POINTS-Reader: Distillation-Free Adaptation of Vision-Language Models for Document Conversion
Generalizable Geometric Image Caption Synthesis
Benefits and Pitfalls of Reinforcement Learning for Language Model Planning: A Theoretical Perspective
Estimating the Empowerment of Language Model Agents
Language Models Can Learn from Verbal Feedback Without Scalar Rewards
Variational Reasoning for Language Models
EPO: Entropy-regularized Policy Optimization for LLM Agents Reinforcement Learning
MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing
Quantile Advantage Estimation for Entropy-Safe Reasoning
LongLive: Real-time Interactive Long Video Generation
Combinatorial Creativity: A New Frontier in Generalization Abilities
Causal Spatio-Temporal Prediction: An Effective and Efficient Multi-Modal Approach
Hunyuan3D-Omni: A Unified Framework for Controllable Generation of 3D Assets
Seedream 4.0: Toward Next-generation Multimodal Image Generation
Tree Search for LLM Agent Reinforcement Learning
SciReasoner: Laying the Scientific Reasoning Ground Across Disciplines
MMR1: Enhancing Multimodal Reasoning with Variance-Aware Sampling and Open Resources