Blog
告别冗长 PDF，一文读懂最新顶会与核心期刊的创新价值。
Faster LLM Inference via Sequential Monte Carlo
TokenGS: Decoupling 3D Gaussian Prediction from Pixels with Learnable Tokens
OFlow: Injecting Object-Aware Temporal Flow Matching for Robust Robotic Manipulation
WebCompass: Towards Multimodal Web Coding Evaluation for Code Language Models
Navigating the Conceptual Multiverse
Does RL Expand the Capability Boundary of LLM Agents? A PASS@(k,T) Analysis
MUA: Mobile Ultra-detailed Animatable Avatars
ReconVLA: An Uncertainty-Guided and Failure-Aware Vision-Language-Action Framework for Robotic Control
TSM-Pose: Topology-Aware Learning with Semantic Mamba for Category-Level Object Pose Estimation
From Procedural Skills to Strategy Genes: Towards Experience-Driven Test-Time Evolution
Why Fine-Tuning Encourages Hallucinations and How to Fix It
LeapAlign: Post-Training Flow Matching Models at Any Generation Step by Building Two-Step Trajectories
Frequency-Aware Flow Matching for High-Quality Image Generation
Diversity Collapse in Multi-Agent LLM Systems: Structural Coupling and Collective Failure in Open-Ended Idea Generation
SynAgent: Generalizable Cooperative Humanoid Manipulation via Solo-to-Cooperative Agent Synergy
Back into Plato's Cave: Examining Cross-modal Representational Convergence at Scale
Branes
Human Cognition in Machines: A Unified Perspective of World Models
OneDrive: Unified Multi-Paradigm Driving with Vision-Language-Action Models
Memory Transfer Learning: How Memories are Transferred Across Domains in Coding Agents
DepCap: Adaptive Block-Wise Parallel Decoding for Efficient Diffusion LM Inference
PRL-Bench: A Comprehensive Benchmark Evaluating LLMs' Capabilities in Frontier Physics Research
GenericAgent: A Token-Efficient Self-Evolving LLM Agent via Contextual Information Density Maximization (V1.0)
MATHNET: A GLOBAL MULTIMODAL BENCHMARK FOR MATHEMATICAL REASONING AND RETRIEVAL
Extending One-Step Image Generation from Class Labels to Text via Discriminative Text Representation
Revisiting a Pain in the Neck: A Semantic Reasoning Benchmark for Language Models
MASS-RAG: Multi-Agent Synthesis Retrieval-Augmented Generation
Can Explicit Physical Feasibility Benefit VLA Learning? An Empirical Study
Train Separately, Merge Together: Modular Post-Training with Mixture-of-Experts
Holography and Optimal Transport: Emergent Wasserstein Spacetime in Harmonic Oscillator, SYK and Krylov Complexity