UniDynamics: Event-RGB Fusion for Unified Future 4D Dynamic Scene Generation
Research
Research News
New papers, breakthroughs and academic AI research
Exact Memory-Time Optimization for Prefix-Cached Language Model Serving
Research
AdaStep: Adaptive Step Credit Weighting for Agentic Reinforcement Learning
Research
Fed-ADApt: Federated Anytime Depth Adaptation for Resource-Aware Medical Image Segmentation
Research
Feedforward Novel View Synthesis for Heterogeneous Cameras
Research
CONTRA: Discovering and Qualifying Behavior-Changing Questions for Selective Clarification in LLM Code Generation
Research
RxnOptBench: Benchmarking LLMs for Reaction-Condition Optimization in Organic Methodology
Research
Passing the Test You Trained On: Re-evaluating Prompt-Injection Detectors for LLM Agents
Research
DuoMatching: Joint-Marginal Distribution Matching for Few-Step Video Generation
Research
Multi-Modal Environment-Aware Beam Management for Massive MIMO: A Geometry-Driven Virtual Base Station Framework
Research
Hardware-Native Joint Sparse-Quantization for Trillion-Scale Mixture-of-Experts
Research
MIRROR: Multipath Quorum Integrity for LLM Multi-Agent Communication
Research