Blog
告别冗长 PDF，一文读懂最新顶会与核心期刊的创新价值。
A Critical Review of Data-Driven Transient Stability Assessment of Power Systems: Principles, Prospects and Challenges
ChatGPT-like large-scale foundation models for prognostics and health management: A survey and roadmaps
LASER couples damage sensing to ESCRT assembly for lysosome repair
Visualizing LLM Latent Space Geometry Through Dimensionality Reduction
Bachmann's bundle pacing: perspectives and recommendations
Pasa: An llm agent for comprehensive academic paper search
SPAR: Scholar Paper Retrieval with LLM-based Agents for Enhanced Academic Search
OMEGA: Can LLMs Reason Outside the Box in Math? Evaluating Exploratory, Compositional, and Transformative Generalization
Epigenetic memory of colitis promotes tumour growth
Nobel Turing Challenge: creating the engine for scientific discovery
Position: Stop Anthropomorphizing Intermediate Tokens as Reasoning/Thinking Traces!
VISTA: Technical Report for the Ego4D Short-Term Object Interaction Anticipation at EgoVis 2026
Advanced Materials - 2025 - Hajalilou - Sustainable Liquid Metal Composites for Soft Electronics and E‐Waste Reduction
Sustainable Liquid Metal Composites for Soft Electronics and E‐Waste Reduction
HRM-Text: Efficient Pretraining Beyond Scaling
AI Scibrief as a Gateway to Research: A Framework for Onboarding Students into New Research Areas
Geometry of Lightning Self-Attention: Identifiability and Dimension
Reflective Empiricism: Bias Reflection and Introspection as a Scientific Method
Toward Generalist Autonomous Research via Hypothesis-Tree Refinement
Entropy-Aware On-Policy Distillation of Language Models
Scaling Reasoning Efficiently via Relaxed On-Policy Distillation
Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Models
UniSD: Towards a Unified Self-Distillation Framework for Large Language Models
TIP: Token Importance in On-Policy Distillation
Asymmetric On-Policy Distillation: Bridging Exploitation and Imitation at the Token Level
Thinking with Visual Primitives
Cybersecurity AI (CAI) Dataset
Immunotherapy drug target identification using machine learning and patient-derived tumour explant validation
LaME: Learning to Think in Latent Space for Multimodal Embedding via Information Bottleneck
Learning to Discover at Test Time