When Verifiable Counts Depend on Wording: Auditing Wording Robustness in Instruction Following
Research
Research News
New papers, breakthroughs and academic AI research
ThyCLIPNet: A BiomedCLIP-Guided Lightweight Attention-Enhanced DeepLabV3+ Framework for Robust Thyroid Nodule Segmentation
Research
Towards Unbiased On-Policy Distillation for Block Diffusion Language Models
Research
The Hidden States Cookbook: A Large-Scale Ablation Study for Noise-Robust Conversational Intent Classification in Industry
Research
Knowing the Rules, Applying the Rules: Evaluating Language Models on Traditional Chinese Bazi
Research
VideoResearchAgent: Grounded Task Synthesis and Sim-to-Real RL for Open-Web Video Research
Research
Are We Measuring Scientific Intelligence? Rethinking the Evaluation of AI Scientists
Research
NAMVIS: Next-Scale Autoregressive Multi-View Image Synthesis
Research
MemStrata: 95% and 90.91% Source-Aware Accuracy on LongMemEval-500 and LoCoMo-1540 with a Local Qwen 3.8 27B Q4_K_M Reader
Research
Do LLMs Understand Sequential Structure? A Controlled Study of Inference and Generation
Research
Zero-Shot Time-Series Question Answering via Decoupled Perception and Reasoning
Research
RubricArmor: Adversarial Evolution Improves LLM-Based Rubric Generation
Research