Papers by Junpeng Wang

6 papers
ETRQA: A Comprehensive Benchmark for Evaluating Event Temporal Reasoning Abilities of Large Language Models (2025.findings-acl)

Copied to clipboard

Challenge: Event temporal reasoning (ETR) is a significant indicator that a large language model understands the physical world.
Approach: They propose a unified taxonomy for event temporal questions and construct a benchmark based on this taxonomies.
Outcome: The proposed taxonomy inherits and expands existing datasets and contains multiple categories of compound questions.
UniGeM: Unifying Data Selection and Mixing via Geometric Exploration and Mining (2026.findings-acl)

Copied to clipboard

Challenge: Large Language Models (LLMs) scaling is limited by data quality and domain mixing and instance selection are two separate problems.
Approach: They propose a framework that unifies mixing and selection without training proxy models or relying on external reference datasets.
Outcome: The proposed framework achieves 2.0 data efficiency over a random baseline and further improves overall performance compared to SOTA methods in reasoning-heavy evaluations and multilingual generalization.
Demystify the Role of Memory in Machine Learning Engineering Agents (2026.findings-acl)

Copied to clipboard

Challenge: Unlike short, reactive exchanges, MLE agents solve tasks through cycles of experimentation and improvement where past errors can inform future success.
Approach: They propose a dynamic coding memory that captures and reuses debugging experiences and integrates it into two representative agent paradigms.
Outcome: The proposed agent model captures and reuses debugging experiences and integrates it into two agent paradigms.
Video Compression Commander: Plug-and-Play Inference Acceleration for Video Large Language Models (2025.emnlp-main)

Copied to clipboard

Challenge: Recent studies have shown that Video Large Language Models (Vide-oLLMs) are efficient at video understanding but lack the quadratic complexity of visual tokens.
Approach: They propose a plug-and-play inference acceleration framework for VideoLLM token compression that quantifies each frame’s uniqueness and adaptively adjusts compression intensity across frames.
Outcome: Extensive experiments on video large language models and benchmarks show that the proposed framework can preserve essential information while reducing redundancy in video sequences.
AEGIS: A Holistic Benchmark for Evaluating Forensic Analysis of AI-Generated Academic Images (2026.acl-long)

Copied to clipboard

Challenge: AEGIS examines whether current models can effectively audit AI-generated images in academic papers.
Approach: They propose a holistic benchmark for forensic analysis of AI-Generated academic ImageS that reveals limitations in academic image forensics.
Outcome: AEGIS compared with existing benchmarks on seven academic categories and features key advances in forensic analysis.
Topic-Aware Contrastive Learning for Abstractive Dialogue Summarization (2021.findings-emnlp)

Copied to clipboard

Challenge: Existing methods to abstractly summarize dialogues are limited to two or more interlocutors.
Approach: They propose to use existing document summarization models to capture the various topic information of a conversation and outline salient facts for the captured topics.
Outcome: The proposed method significantly outperforms baselines and achieves new state-of-the-art performance on benchmark datasets.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations