Faithful Chart Generation for Multimodal Deep Research: Frame-Evidence Co-Adaptation
Research
Research News
New papers, breakthroughs and academic AI research
MEGA: Object-Level Mesh Extraction from 3D Gaussian Splatting via Spatial Visual Distillation
Research
Architectural Sampling: Test-Time Scaling via Computational Diversity in Frozen Vision-Language Models
Research
Towards Fast and Disentangled Counterfactuals for Visual Foundation Models
Research
When Do Biological Reasoning Models Use Their Biological Inputs?
Research
Sharpen Before You Adapt: Data-Free Entry-State Sharpening for Test-Time Reinforcement Learning
Research
Rate-Optimal Algorithm for Adversarial Linear CMDPs
Research
Platonic Task Arithmetic
Research
ATI-VLA: Action-Centric Predictive Vision-Language-Action Models via Actionable Alignment Then Adaptive Injection
Research
Generalist Representation, Specialist Detection: TS-Router for Time-Series Anomaly Detection
Research
Q-SPT: Learnable Query-Based Compression for Low-Frame-Rate Speech Tokenization
Research
Mean field games as a tool for AI safety: a worked example from the July 2026 Hugging Face incident
Research