Why Fine-Tuning Encourages Hallucinations and How to Fix It Paper • 2604.15574 • Published 20 days ago • 22
Why Fine-Tuning Encourages Hallucinations and How to Fix It Paper • 2604.15574 • Published 20 days ago • 22
Alignment Makes Language Models Normative, Not Descriptive Paper • 2603.17218 • Published Mar 17 • 46
Thinking to Recall: How Reasoning Unlocks Parametric Knowledge in LLMs Paper • 2603.09906 • Published Mar 10 • 75
Alterbute: Editing Intrinsic Attributes of Objects in Images Paper • 2601.10714 • Published Jan 15 • 31
Runtime error Agents 2 Inner Lexicon 😻 2 demonstrating how the model retrieve words by sub-word token
Runtime error Agents 2 Inner Lexicon 😻 2 demonstrating how the model retrieve words by sub-word token
Beyond Transcription: Mechanistic Interpretability in ASR Paper • 2508.15882 • Published Aug 21, 2025 • 89
Story2Board: A Training-Free Approach for Expressive Storyboard Generation Paper • 2508.09983 • Published Aug 13, 2025 • 70
StressTest: Can YOUR Speech LM Handle the Stress? Paper • 2505.22765 • Published May 28, 2025 • 17
Don't Overthink it. Preferring Shorter Thinking Chains for Improved LLM Reasoning Paper • 2505.17813 • Published May 23, 2025 • 58
Runtime error Agents 2 Inner Lexicon 😻 2 demonstrating how the model retrieve words by sub-word token
Follow the Flow: On Information Flow Across Textual Tokens in Text-to-Image Models Paper • 2504.01137 • Published Apr 1, 2025 • 21
From Tokens to Words: On the Inner Lexicon of LLMs Paper • 2410.05864 • Published Oct 8, 2024 • 1
From Tokens to Words: On the Inner Lexicon of LLMs Paper • 2410.05864 • Published Oct 8, 2024 • 1 • 1