From the 1 of 55 linked papers with an AI index.
55 papers
ProgramTab: Boosting Table Reasoning of LLMs via Programmatic Paradigm
Pei Guo, Enjie Liu, Yunzhi Tan +6
The paper introduces ProgramTab, a framework that uses in‑context learning and Python code generation to preprocess large tables and extract relevant sub‑tables, enabling large lan…
Homer: Understanding Long-form Videos with Hierarchical Memory and Agentic Reasoning
Yixin Ji, Fanghua Ye, Juntao Li +5
Multimodal large language models excel on short clips but struggle on hour-long videos in an online setting, where frames are processed incrementally under limited memory. Existing…
IS-CoT: Breaking the Long-form Generation Collapse via Interleaved Structural Thinking
Zechen Sun, Yuyang Sun, Zecheng Tang +6
Generating coherent and controllable long-form content remains a persistent challenge for Large Language Models (LLMs). While reasoning-enhanced models have demonstrated success in…
MMLongEmbed: Benchmarking Multimodal Embedding Models in Long-Context Scenarios
Haitian Wang, Ruoxi Sun, Quantong Qiu +5
Recent advancements have significantly expanded the theoretical context windows of Multimodal Embedding Models (MEMs). However, larger context windows do not necessarily translate…
Mechanistic Insights into Functional Sparsity in Multimodal LLMs via CoRe Heads
Ruoxi Sun, Quantong Qiu, Juntao Li +3
While Multimodal Large Language Models (MLLMs) demonstrate remarkable proficiency on complex vision-language tasks, the mechanisms by which they extract query-relevant visual featu…
EviRerank: Adaptive Evidence Construction for Long-Document LLM Reranking
Minghan Li, Eric Gaussier, Juntao Li +1
Decoder-only LLM rerankers struggle with long documents: inference is costly and relevance signals can be diluted by irrelevant context. Motivated by a diagnostic attention analysi…