OmniConfess: Eliciting Token Confessions to Mitigate Omni-Modal Hallucination
Research
Research News
New papers, breakthroughs and academic AI research
RYOPO: Bringing End-to-End Category-Level Object Pose Estimation into Real Time
Research
Found but Not Read: When Extracted Text Closes the Retrieval-Reading Gap in Document Vision-Language Models
Research
Recursive Self-Improvement in Unified Multimodal Models
Research
HyperThink: Text-to-Parameter Hypernetworks for Efficient Reasoning
Research
ViTok: Improving Dense Semantics in AM-RADIO-Style Multi-Teacher Distillation with PHI-S and Masked Image Modelling
Research
On the Chain-of-Thought Monitorability of Looped Language Models
Research
MetaRubric: Learning to Reward for Rubric-Based Reinforcement Learning
Research
Revealing Epistemic Uncertainty in MLLMs via Causal-Invariant Masking
Research
The Geometry of Knowledge Accessibility in Large Language Models
Research
Unmasking Propaganda: A Comparative Analysis of Masked and Causal Language Models
Research
PAPER2LLM++: Continual Self-Evolution of LLMs from Research Papers
Research