Blog
告别冗长 PDF，一文读懂最新顶会与核心期刊的创新价值。
OmniReason: A Temporal-Guided Vision-Language-Action Framework for Autonomous Driving
2507.04049v3
There Will Be a Scientific Theory of Deep Learning
Low-Rank Adaptation Redux for Large Models
From Tokens to Concepts: Leveraging SAE for SPLADE
KNOWLEDGE‐BASED SYSTEMS
Computer Vision and Image Understanding
Multimodal foundation model and benchmark for comprehensive retinal OCT image analysis
Meta-Causal Learning for Single Domain Generalization
Rethinking On-Policy Distillation
Hyperloop Transformers
Causal Concept Graphs in LLM Latent Space for Stepwise Reasoning
Multi-Token Prediction via Self-Distillation
UR$^2$: Unify RAG and Reasoning through Reinforcement Learning
DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond
From Skills to Talent: Organising Heterogeneous Agents as a Real-World Company
Progress and prospects of thermally conductive/flame-retardant integrated polymer composites
Lightweight Retrieval-Augmented Generation and Large Language Model-Based Modeling for Scalable Patient-Trial Matching
Machining of ZrO2 ceramics with PCD and CBN cutting tools
How Well Does Generative Recommendation Generalize?
Traffic expertise meets residual RL: Knowledge-informed model-based residual reinforcement learning for CAV trajectory control
Farewell to Item IDs: Unlocking the Scaling Potential of Large Ranking Models via Semantic Tokens
Modular Interface Adapters for Cross-Environment Reinforcement Fine-Tuning Transfer
V-MAGE: A Game Evaluation Framework for Assessing Vision-Centric Capabilities in Multimodal Large Language Models
Learning an Image Editing Model without Image Editing Pairs
EMOE: Modality-Specific Enhanced Dynamic Emotion Experts
Multimodal Sentiment Analysis With Mutual Information-Based Disentangled Representation Learning
Thinking with Visual Primitives
High-fidelity collisional quantum gates with fermionic atoms