Q-Filters: Leveraging QK Geometry for Efficient KV Cache Compression Paper • 2503.02812 • Published 10 days ago • 9
Lost in Time: Clock and Calendar Understanding Challenges in Multimodal LLMs Paper • 2502.05092 • Published Feb 7 • 7
PosterSum: A Multimodal Benchmark for Scientific Poster Summarization Paper • 2502.17540 • Published 18 days ago • 2
Lost in Time: Clock and Calendar Understanding Challenges in Multimodal LLMs Paper • 2502.05092 • Published Feb 7 • 7
CoMAT: Chain of Mathematically Annotated Thought Improves Mathematical Reasoning Paper • 2410.10336 • Published Oct 14, 2024 • 2
Adaptive Computation Modules: Granular Conditional Computation For Efficient Inference Paper • 2312.10193 • Published Dec 15, 2023 • 1
A Simple and Effective $L_2$ Norm-Based Strategy for KV Cache Compression Paper • 2406.11430 • Published Jun 17, 2024 • 24
Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering Paper • 2410.15999 • Published Oct 21, 2024 • 20
Analysing the Residual Stream of Language Models Under Knowledge Conflicts Paper • 2410.16090 • Published Oct 21, 2024 • 7
CoMAT: Chain of Mathematically Annotated Thought Improves Mathematical Reasoning Paper • 2410.10336 • Published Oct 14, 2024 • 2
Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering Paper • 2410.15999 • Published Oct 21, 2024 • 20
Analysing the Residual Stream of Language Models Under Knowledge Conflicts Paper • 2410.16090 • Published Oct 21, 2024 • 7
DeCoRe: Decoding by Contrasting Retrieval Heads to Mitigate Hallucinations Paper • 2410.18860 • Published Oct 24, 2024 • 11
MovieSum: An Abstractive Summarization Dataset for Movie Screenplays Paper • 2408.06281 • Published Aug 12, 2024 • 9
Select and Summarize: Scene Saliency for Movie Script Summarization Paper • 2404.03561 • Published Apr 4, 2024 • 2
A Simple and Effective $L_2$ Norm-Based Strategy for KV Cache Compression Paper • 2406.11430 • Published Jun 17, 2024 • 24
The Hallucinations Leaderboard -- An Open Effort to Measure Hallucinations in Large Language Models Paper • 2404.05904 • Published Apr 8, 2024 • 9