Harness Compilation: Which Decisions Should a Small Vision-Language Model Keep?
Research
Research News
New papers, breakthroughs and academic AI research
LLM-IDEA: Identifiability-Driven Experimental Agent for Autonomous Discovery of Mechanistic World Models
Research
Nullify: Null-Space Activation Steering for Training-Free LLM Unlearning
Research
AliO: Output Alignment Matters in Long-Term Time Series Forecasing
Research
Beyond Owls: Subliminal Learning Can Transfer Learned Capabilities and Backdoors
Research
Open-ended Scientific Discovery with Possibilistic Reasoning
Research
GPU-Accelerated Computation of Persistent Homology for Topological Analysis of Image Data
Research
Fluid-Gen-Zero: Grounding Pretrained Video Generators in Physics without Training
Research
Expression-Diverse References for Identity-Preserving Video Generation
Research
When Lower Reconstruction Loss Hurts: Distributionally Robust Refinement for Low-Bit LLM Quantization
Research
Region-Aware CLS Token Augmentation for Fine-Grained Image Retrieval
Research
Clinician use of language models diverges from how the models are evaluated
Research