logo
today local_bar
Long-context

5 papers across 3 sessions

Poster Session 1

2 papers
Wednesday, December 3, 2025 · 11:00 AM → 2:00 PM
Exhibit Hall C,D,E
Temporal Chain of Thought: Long-Video Understanding by Thinking in Frames
#4801 · Anurag Arnab, Ahmet Iscen, Mathilde Caron, Alireza Fathi, Cordelia Schmid

We propose an inference-strategy for long-video QA, which substantially improves the accuracy of a VLM by curating its input context.
Absence Bench: Language Models Can’t See What’s Missing
#1309 Spotlight · Harvey Yiyun Fu, Aryan Shrivastava, Jared Moore, Peter West, Chenhao Tan, Ari Holtzman

Poster Session 3

2 papers
Thursday, December 4, 2025 · 11:00 AM → 2:00 PM
Exhibit Hall C,D,E
NeedleInATable: Exploring Long-Context Capability of Large Language Models towards Long-Structured Tables
#3803 · Lanrui Wang, Mingyu Zheng, Hongyin Tang, Zheng Lin, Yanan Cao, Jingang Wang, Xunliang Cai, Weiping Wang
ChunkKV: Semantic-Preserving KV Cache Compression for Efficient Long-Context LLM Inference
#3306 · Xiang Liu, Zhenheng Tang, Peijie Dong, Zeyu Li, Liuyue, Bo Li, Xuming Hu, Xiaowen Chu

Poster Session 5

1 paper
Friday, December 5, 2025 · 11:00 AM → 2:00 PM
Exhibit Hall C,D,E
LooGLE v2: Are LLMs Ready for Real World Long Dependency Challenges?
#5102 · Ziyuan He, Yuxuan Wang, Jiaqi Li, Kexin Liang, Muhan Zhang

A novel real-world benchmark for long dependency understanding.