RealSWE: A Compositional Evaluation of Coding Agents under Realistic User Requests
Research
Research News
New papers, breakthroughs and academic AI research
BuzzASR: A Swarm of 100+ Monolingual Speech Recognition Models
Research
Can LLMs Discover Scientific Laws in Real and Parallel Worlds?
Research
DramaChain Bench: An End-to-End Benchmark for Short-Drama Generation
Research
3ViewSense: Spatial and Mental Perspective Reasoning from Orthographic Views in Vision-Language Models
Research
Decoupling Time and Space: A Temporally Conditioned Refinement for EEG Source Imaging
Research
Hidden in the Request: Explaining Unethical LLM Compliance through Token Relevance
Research
To Learn is to Wander: Learning Across Graphs and Tasks with Random Walks
Research
NxN E-valuation: Hypothesis Certification via a Conformal CRT Null
Research
Systematic Hazard Sampling: Minimal-Variance Inference for Discrete Diffusion and Flow Models
Research
Live Interactive Training for Video Segmentation
Research
The Hidden Frame: How Large Language Models Impact Democratic Society
Research