ICLR 2026, Rio de Janeiro, Brazil
Highlights and Selected Papers
Posted on 11th August 2026
Highlighted Papers
- Understanding Task Vectors in In-Context Learning: Emergence, Functionality, and Limitations
- Model Collapse Is Not a Bug but a Feature in Machine Unlearning for LLMs
- Enhancing Hallucination Detection through Noise Injection
- Attribution Guided Decoding
- When RAG Hurts: Diagnosing and Mitigating Attention Distraction in Retrieval-Augmented LVLMs
- Enhancing Trust in Large Language Models via Uncertainty-Calibrated Fine-Tuning
- Verbosity tradeoffs and the impact of scale on the faithfulness of LLM self-explanations
- Mechanics of Bias and Reasoning: Interpreting the Impact of Chain-of-Thought Prompting on Gender Bias in LLMs
- Attention smoothing is all you need for unlearning