Shallow Queries, Mature Values: Depth-Asynchronous Self-Speculation for Looped Transformers
Research
Research News
New papers, breakthroughs and academic AI research
Brain-SAD: A Brain-Inspired Safe Autonomous Driving Control Framework with Dynamic Fear-Oriented Constraint on Dual-Policy
Research
PARSER: Read in Parallel, Reason in Depth for Long-Context LLM Agents
Research
Do LLM Agents Execute the Plans They Declare? From Planning-Mode Declaration to Pattern-Specific Execution
Research
Why Cross-Skeleton Retargeting Is Non-Identifiable: Structural Limits of Generative Motion Models
Research
KiT: A Foundation Model for Financial Time-Series Forecasting using DiffusionTransformers
Research
Recall Is Not Protection: Evaluating Safety Monitors Against Model Compliance
Research
Probability is Not Enough: Exploring and Counting Divergent Tokens for Reasoning Uncertainty Quantification in LLMs
Research
NeuronEye: Query-Guided Visual Concept Activation for Vision-Language Reasoning
Research
Thinking Before Thinking: Scaling Agentic Inference Through Meta-Reasoning
Research
Decoding One Safety Trigger Token for Balancing Safety and Usability in Large Language Models
Research
Scalable GNN-based Knowledge Graph Representation Learning with Efficient Message Passing
Research