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

TOPReward: Token Probabilities as Hidden Zero-Shot Rewards for Robotics

ManCAR: Manifold-Constrained Latent Reasoning with Adaptive Test-Time Computation for Sequential Recommendation































TOPReward: Token Probabilities as Hidden Zero-Shot Rewards for Robotics

ManCAR: Manifold-Constrained Latent Reasoning with Adaptive Test-Time Computation for Sequential Recommendation






























VLANeXt: Recipes for Building Strong VLA Models
A Very Big Video Reasoning Suite
Selective Training for Large Vision Language Models via Visual Information Gain
DeepVision-103K: A Visually Diverse, Broad-Coverage, and Verifiable Mathematical Dataset for Multimodal Reasoning
SARAH: Spatially Aware Real-time Agentic Humans
EgoPush: Learning End-to-End Egocentric Multi-Object Rearrangement for Mobile Robots
Generated Reality: Human-centric World Simulation using Interactive Video Generation with Hand and Camera Control
VESPO: Variational Sequence-Level Soft Policy Optimization for Stable Off-Policy LLM Training
Arcee Trinity Large Technical Report
Frontier AI Risk Management Framework in Practice: A Risk Analysis Technical Report v1.5
Unified Latents (UL): How to train your latents
Mobile-Agent-v3.5: Multi-platform Fundamental GUI Agents
SpargeAttention2: Trainable Sparse Attention via Hybrid Top-k+Top-p Masking and Distillation Fine-Tuning
AutoWebWorld: Synthesizing Infinite Verifiable Web Environments via Finite State Machines
Bounded Model Checking for Unbounded Client Server Systems
How Much Reasoning Do Retrieval-Augmented Models Add beyond LLMs? A Benchmarking Framework for Multi-Hop Inference over Hybrid Knowledge
The Vision Wormhole: Latent-Space Communication in Heterogeneous Multi-Agent Systems
Panini: Continual Learning in Token Space via Structured Memory
ResearchGym: Evaluating Language Model Agents on Real-World AI Research
Learning to Configure Agentic AI Systems
Does Socialization Emerge in AI Agent Society? A Case Study of Moltbook
Sanity Checks for Sparse Autoencoders: Do SAEs Beat Random Baselines?
SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks
GLM-5: from Vibe Coding to Agentic Engineering
BitDance: Scaling Autoregressive Generative Models with Binary Tokens
REDSearcher: A Scalable and Cost-Efficient Framework for Long-Horizon Search Agents
Qute: Towards Quantum-Native Database
InnoEval: On Research Idea Evaluation as a Knowledge-Grounded, Multi-Perspective Reasoning Problem
Query as Anchor: Scenario-Adaptive User Representation via Large Language Model
SemanticMoments: Training-Free Motion Similarity via Third Moment Features
VLANeXt: Recipes for Building Strong VLA Models
A Very Big Video Reasoning Suite
Selective Training for Large Vision Language Models via Visual Information Gain
DeepVision-103K: A Visually Diverse, Broad-Coverage, and Verifiable Mathematical Dataset for Multimodal Reasoning
SARAH: Spatially Aware Real-time Agentic Humans
EgoPush: Learning End-to-End Egocentric Multi-Object Rearrangement for Mobile Robots
Generated Reality: Human-centric World Simulation using Interactive Video Generation with Hand and Camera Control
VESPO: Variational Sequence-Level Soft Policy Optimization for Stable Off-Policy LLM Training
Arcee Trinity Large Technical Report
Frontier AI Risk Management Framework in Practice: A Risk Analysis Technical Report v1.5
Unified Latents (UL): How to train your latents
Mobile-Agent-v3.5: Multi-platform Fundamental GUI Agents
SpargeAttention2: Trainable Sparse Attention via Hybrid Top-k+Top-p Masking and Distillation Fine-Tuning
AutoWebWorld: Synthesizing Infinite Verifiable Web Environments via Finite State Machines
Bounded Model Checking for Unbounded Client Server Systems
How Much Reasoning Do Retrieval-Augmented Models Add beyond LLMs? A Benchmarking Framework for Multi-Hop Inference over Hybrid Knowledge
The Vision Wormhole: Latent-Space Communication in Heterogeneous Multi-Agent Systems
Panini: Continual Learning in Token Space via Structured Memory
ResearchGym: Evaluating Language Model Agents on Real-World AI Research
Learning to Configure Agentic AI Systems
Does Socialization Emerge in AI Agent Society? A Case Study of Moltbook
Sanity Checks for Sparse Autoencoders: Do SAEs Beat Random Baselines?
SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks
GLM-5: from Vibe Coding to Agentic Engineering
BitDance: Scaling Autoregressive Generative Models with Binary Tokens
REDSearcher: A Scalable and Cost-Efficient Framework for Long-Horizon Search Agents
Qute: Towards Quantum-Native Database
InnoEval: On Research Idea Evaluation as a Knowledge-Grounded, Multi-Perspective Reasoning Problem
Query as Anchor: Scenario-Adaptive User Representation via Large Language Model
SemanticMoments: Training-Free Motion Similarity via Third Moment Features