Blog
No more endless PDFs. Discover the core value of the latest top-tier research in one article.
Vectorizing the Trie: Efficient Constrained Decoding for LLM-based Generative Retrieval on Accelerators
CRAG: Can 3D Generative Models Help 3D Assembly?
DySL-VLA: Efficient Vision-Language-Action Model Inference via Dynamic-Static Layer-Skipping for Robot Manipulation
MobilityBench: A Benchmark for Evaluating Route-Planning Agents in Real-World Mobility Scenarios
Training Agents to Self-Report Misbehavior
Detection and Recognition: A Pairwise Interaction Framework for Mobile Service Robots
UniScale: Unified Scale-Aware 3D Reconstruction for Multi-View Understanding via Prior Injection for Robotic Perception
TESS Planet Occurrence Rates Reveal the Disappearance of the Radius Valley Around Mid-to-Late M Dwarfs
Iterative Closed-Loop Motion Synthesis for Scaling the Capabilities of Humanoid Control
A Bayesian approach to out-of-sample network reconstruction
Search-P1: Path-Centric Reward Shaping for Stable and Efficient Agentic RAG Training
ArchAgent: Agentic AI-driven Computer Architecture Discovery
DyaDiT: A Multi-Modal Diffusion Transformer for Socially Favorable Dyadic Gesture Generation
A data- and compute-efficient chest X-ray foundation model beyond aggressive scaling
ParamMem: Augmenting Language Agents with Parametric Reflective Memory
Codified Context: Infrastructure for AI Agents in a Complex Codebase
SODA-CitrON: Static Object Data Association by Clustering Multi-Modal Sensor Detections Online
VRSL:Exploring the Comprehensibility of 360-Degree Camera Feeds for Sign Language Communication in Virtual Reality
Relativistic Tidal Dissipation and the Gravitational-wave Signal of a White Dwarf Orbiting an Intermediate-Mass Black Hole
PackUV: Packed Gaussian UV Maps for 4D Volumetric Video
Vibe Researching as Wolf Coming: Can AI Agents with Skills Replace or Augment Social Scientists?
MSJoE: Jointly Evolving MLLM and Sampler for Efficient Long-Form Video Understanding
Entropy-Controlled Flow Matching
Duel-Evolve: Reward-Free Test-Time Scaling via LLM Self-Preferences
Pixel2Catch: Multi-Agent Sim-to-Real Transfer for Agile Manipulation with a Single RGB Camera
Stable Adaptive Thinking via Advantage Shaping and Length-Aware Gradient Regulation
AgentSentry: Mitigating Indirect Prompt Injection in LLM Agents via Temporal Causal Diagnostics and Context Purification
A Scaling Law for Bandwidth Under Quantization
Spherically Symmetric Gravity on a Graph I: Theoretical Foundations
PATRA: Pattern-Aware Alignment and Balanced Reasoning for Time Series Question Answering