Blog
告别冗长 PDF，一文读懂最新顶会与核心期刊的创新价值。
Glove2Hand: Synthesizing Natural Hand-Object Interaction from Multi-Modal Sensing Gloves
Revisiting the Excess of Bar-like Structures in TNG50 Early-type Galaxies: Consistency and Tension with Observations
LongCat-Flash-Prover: Advancing Native Formal Reasoning via Agentic Tool-Integrated Reinforcement Learning
Autoregressive vs. Masked Diffusion Language Models: A Controlled Comparison
Chiral Spin Liquid in Rydberg Atom Arrays
ThinkJEPA: Empowering Latent World Models with Large Vision-Language Reasoning Model
Omni-WorldBench: Towards a Comprehensive Interaction-Centric Evaluation for World Models
WebNavigator: Global Web Navigation via Interaction Graph Retrieval
AgenticRec: End-to-End Tool-Integrated Policy Optimization for Ranking-Oriented Recommender Agents
WorldCache: Content-Aware Caching for Accelerated Video World Models
Manifold-Aware Exploration for Reinforcement Learning in Video Generation
IGV-RRT: Prior-Real-Time Observation Fusion for Active Object Search in Changing Environments
VideoDetective: Clue Hunting via both Extrinsic Query and Intrinsic Relevance for Long Video Understanding
DexDrummer: In-Hand, Contact-Rich, and Long-Horizon Dexterous Robot Drumming
PAM: A Pose-Appearance-Motion Engine for Sim-to-Real HOI Video Generation
The Universal Normal Embedding
One Model, Two Markets: Bid-Aware Generative Recommendation
PEARL: Personalized Streaming Video Understanding Model
Seed1.8 Model Card: Towards Generalized Real-World Agency
Generalized Discrete Diffusion from Snapshots
Mechanisms of Introspective Awareness
FreeArtGS: Articulated Gaussian Splatting Under Free-moving Scenario
StreamingClaw Technical Report
UniDex: A Robot Foundation Suite for Universal Dexterous Hand Control from Egocentric Human Videos
2K Retrofit: Entropy-Guided Efficient Sparse Refinement for High-Resolution 3D Geometry Prediction
UniMotion: A Unified Framework for Motion-Text-Vision Understanding and Generation
ProactiveBench: Benchmarking Proactiveness in Multimodal Large Language Models
SkillProbe: Security Auditing for Emerging Agent Skill Marketplaces via Multi-Agent Collaboration
SpatialBoost: Enhancing Visual Representation through Language-Guided Reasoning
Breaking the Capability Ceiling of LLM Post-Training by Reintroducing Markov States