Blog
告别冗长 PDF，一文读懂最新顶会与核心期刊的创新价值。
SpUDD: Superpower Contouring of Unsigned Distance Data
SkillLearnBench: Benchmarking Continual Learning Methods for Agent Skill Generation on Real-World Tasks
FLASH: Fast Learning via GPU-Accelerated Simulation for High-Fidelity Deformable Manipulation in Minutes
HoWToBench: Holistic Evaluation for LLM's Capability in Human-level Writing using Tree of Writing
AIT Academy: Cultivating the Complete Agent with a Confucian Three-Domain Curriculum
HP-Edit: A Human-Preference Post-Training Framework for Image Editing
Quantum mechanics over real numbers fully reproduces standard quantum theory
Topological Word for Non-Abelian Topological Insulators
Unconventional Quantum Criticality in Long-Range Spin-1 Chains: Insights from Entanglement Entropy and Bipartite Fluctuations
Geometry-Guided 3D Visual Token Pruning for Video-Language Models
LLMs Know They're Wrong and Agree Anyway: The Shared Sycophancy-Lying Circuit
Qubit Routing for (Almost) Free
Mitigating Multimodal Hallucination via Phase-wise Self-reward
ProMMSearchAgent: A Generalizable Multimodal Search Agent Trained with Process-Oriented Rewards
Camera Control for Text-to-Image Generation via Learning Viewpoint Tokens
CreativeGame:Toward Mechanic-Aware Creative Game Generation
Semantic Recall for Vector Search
Fault-Tolerant Quantum Computing with Trapped Ions: The Walking Cat Architecture
Asymptotic charges as detectors and the memory effect in massive QED and perturbative quantum gravity
Let ViT Speak: Generative Language-Image Pre-training
Model Spec Midtraining: Improving How Alignment Training Generalizes
Mamoda2.5: Enhancing Unified Multimodal Model with DiT-MoE
RLDX-1 Technical Report
HeavySkill: Heavy Thinking as the Inner Skill in Agentic Harness
A Theory of Generalization in Deep Learning
T$^2$PO: Uncertainty-Guided Exploration Control for Stable Multi-Turn Agentic Reinforcement Learning
OpenSeeker-v2: Pushing the Limits of Search Agents with Informative and High-Difficulty Trajectories
Representation Fréchet Loss for Visual Generation
World Model for Robot Learning: A Comprehensive Survey
On Training Large Language Models for Long-Horizon Tasks: An Empirical Study of Horizon Length