6 papers
SkipKV: Selective Skipping of KV Generation and Storage for Efficient Inference with Large Reasoning Models
Jiayi Tian, Seyedarmin Azizi, Yequan Zhao +7
Large reasoning models (LRMs) often incur significant key-value (KV) cache overhead, due to their linear growth with the verbose chain-of-thought (CoT) reasoning. This incurs both…
Improving the Throughput of Diffusion-based Large Language Models via a Training-Free Confidence-Aware Calibration
Jucheng Shen, Gaurav Sarkar, Yeonju Ro +4
We present CadLLM, a training-free method to accelerate the inference throughput of diffusion-based LLMs (dLLMs). We first investigate the dynamic nature of token unmasking confide…
Harnessing Object Grounding for Time-Sensitive Video Understanding
Tz-Ying Wu, Sharath Nittur Sridhar, Subarna Tripathi
We propose to improve the time-sensitive video understanding (TSV) capability of video large language models (Video-LLMs) with grounded objects (GO). We hypothesize that TSV tasks…
EASG-Bench: Video Q&A Benchmark with Egocentric Action Scene Graphs
Ivan Rodin, Tz-Ying Wu, Kyle Min +4
We introduce EASG-Bench, a question-answering benchmark for egocentric videos where the question-answering pairs are created from spatio-temporally grounded dynamic scene graphs ca…
Toward Scalable Video Narration: A Training-free Approach Using Multimodal Large Language Models
Tz-Ying Wu, Tahani Trigui, Sharath Nittur Sridhar +2
In this paper, we introduce VideoNarrator, a novel training-free pipeline designed to generate dense video captions that offer a structured snapshot of video content. These caption…
LVLM-Compress-Bench: Benchmarking the Broader Impact of Large Vision-Language Model Compression
Souvik Kundu, Anahita Bhiwandiwalla, Sungduk Yu +6
Despite recent efforts in understanding the compression impact on large language models (LLMs) in terms of their downstream task performance and trustworthiness on relatively simpl…