Instruction-Tuned Video-Audio Models Elucidate Functional Specialization in the Brain Paper • 2506.08277 • Published about 1 month ago • 1
Leveraging Vision-Language Pre-training for Human Activity Recognition in Still Images Paper • 2506.13458 • Published 24 days ago
Making Retrieval-Augmented Language Models Robust to Irrelevant Context Paper • 2310.01558 • Published Oct 2, 2023 • 2
How Optimal is Greedy Decoding for Extractive Question Answering? Paper • 2108.05857 • Published Aug 12, 2021
Transformer Language Models without Positional Encodings Still Learn Positional Information Paper • 2203.16634 • Published Mar 30, 2022 • 5
DRAGged into Conflicts: Detecting and Addressing Conflicting Sources in Search-Augmented LLMs Paper • 2506.08500 • Published about 1 month ago • 7
Don't "Overthink" Passage Reranking: Is Reasoning Truly Necessary? Paper • 2505.16886 • Published May 22 • 6
Beyond Markovian: Reflective Exploration via Bayes-Adaptive RL for LLM Reasoning Paper • 2505.20561 • Published May 26 • 7
Date Fragments: A Hidden Bottleneck of Tokenization for Temporal Reasoning Paper • 2505.16088 • Published May 22 • 3
view post Post 1934 Super grateful to @marriola for the release of the block diffusion code and model. I'm generating text with diffusion locally! Couldn't be more pleased. See translation 2 replies · 👍 4 4 👀 1 1 + Reply
Retrofitting (Large) Language Models with Dynamic Tokenization Paper • 2411.18553 • Published Nov 27, 2024 • 2
Cross-Tokenizer Distillation via Approximate Likelihood Matching Paper • 2503.20083 • Published Mar 25 • 1
Can LVLMs and Automatic Metrics Capture Underlying Preferences of Blind and Low-Vision Individuals for Navigational Aid? Paper • 2502.14883 • Published Feb 15
Sightation Counts: Leveraging Sighted User Feedback in Building a BLV-aligned Dataset of Diagram Descriptions Paper • 2503.13369 • Published Mar 17 • 7
Collapse of Dense Retrievers: Short, Early, and Literal Biases Outranking Factual Evidence Paper • 2503.05037 • Published Mar 6 • 4