Blog
告别冗长 PDF，一文读懂最新顶会与核心期刊的创新价值。
Tabular foundation models for in-context prediction of molecular properties
Adolf Hurwitz and the Fundamental Theorem of Galois Theorie: The Königsberg Lectures of 1890-1891
Beyond One-Size-Fits-All: Adaptive Test-Time Augmentation for Sequential Recommendation
The Neptunian ridge as a natural outcome of high-eccentricity tidal migration
Qwen3.5-Omni Technical Report
(1D) Ordered Tokens Enable Efficient Test-Time Search
Prefill-as-a-Service: KVCache of Next-Generation Models Could Go Cross-Datacenter
AgentV-RL: Scaling Reward Modeling with Agentic Verifier
When Can LLMs Learn to Reason with Weak Supervision?
Representation Before Training: A Fixed-Budget Benchmark for Generative Medical Event Models
Neural Garbage Collection: Learning to Forget while Learning to Reason
Skill-RAG: Failure-State-Aware Retrieval Augmentation via Hidden-State Probing and Skill Routing
World-Value-Action Model: Implicit Planning for Vision-Language-Action Systems
Fisher Decorator: Refining Flow Policy via A Local Transport Map
Elucidating the SNR-t Bias of Diffusion Probabilistic Models
ClawEnvKit: Automatic Environment Generation for Claw-Like Agents
The Amazing Stability of Flow Matching
CT Open: An Open-Access, Uncontaminated, Live Platform for the Open Challenge of Clinical Trial Outcome Prediction
Aligning What Vision-Language Models See and Perceive with Adaptive Information Flow
HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds
CoEvolve: Training LLM Agents via Agent-Data Mutual Evolution
Efficient Video Diffusion Models: Advancements and Challenges
Latent Fourier Transform
Unmasking the Illusion of Embodied Reasoning in Vision-Language-Action Models
Audio-DeepThinker: Progressive Reasoning-Aware Reinforcement Learning for High-Quality Chain-of-Thought Emergence in Audio Language Models
On the Gamma-ray Efficiency of Superluminous Supernovae: Potential Detections and Population-Level Constraints
Ground state preparation in two-dimensional pure $\mathbb{Z}_2$ lattice gauge theory via deterministic quantum imaginary time evolution
Beyond Text-Dominance: Understanding Modality Preference of Omni-modal Large Language Models
CiPO: Counterfactual Unlearning for Large Reasoning Models through Iterative Preference Optimization
Cut Your Losses! Learning to Prune Paths Early for Efficient Parallel Reasoning