Papers by Junhao Xu

10 papers
Lil: Less is Less When Applying Post-Training Sparse-Attention Algorithms in Long-Decode Stage (2026.findings-acl)

Copied to clipboard

Challenge: Prior work typically decomposes inference into prefill and decode stages, with the decode stage dominating total latency.
Approach: They propose an algorithm that detects threshold where information loss exceeds information gain during sparse decoding to reduce token consumption by up to 90% and a marginal accuracy degradation of less than 2%.
Outcome: The proposed algorithm reduces token consumption by 90% with a marginal accuracy degradation of less than 2% across reasoning-intensive benchmarks.
PairCoder: Pair Programming-Inspired Two-Agent Collaboration for Code Generation (2026.findings-acl)

Copied to clipboard

Challenge: Existing multi agent frameworks for large language models are brittle on code generation tasks.
Approach: They propose a framework that brings pair programming to autonomous LLM collaboration.
Outcome: Using PairCoder, large language models achieve better results on code generation tasks and reduce token usage by 40% to 70% on eight representative backbones.
SERE: Structural Example Retrieval for Enhancing LLMs in Event Causality Identification (2026.findings-acl)

Copied to clipboard

Challenge: Large Language Models (LLMs) have demonstrated strong performance across various NLP tasks, but their effectiveness in ECI remains limited due to biases in causal reasoning.
Approach: They propose a structural example retrieval framework that leverages LLMs’ few-shot learning capabilities to help LLM models in ECI.
Outcome: The proposed framework leverages LLMs’ few-shot learning capabilities to guide LLM models in causal reasoning, mitigating bias and improving accuracy.
Editing the Moving World: Model Editing for Video LLMs (2026.acl-long)

Copied to clipboard

Challenge: Existing models for knowledge editing focus on knowledge-level or static visual domains, overlooking dynamic semantics.
Approach: They propose a benchmark for modeling large language models using six representative models . they analyze the strengths and limitations of existing models and identify new directions .
Outcome: The proposed benchmark extends existing models from static modalities to dynamic video scenarios.
TCPO: Thought-Centric Preference Optimization for Effective Embodied Decision-making (2025.emnlp-main)

Copied to clipboard

Challenge: Existing post-SFT methods for embodied AI are constrained by sparse rewards and action-only optimization, resulting in low sample efficiency, poor consistency, and model degradation.
Approach: They propose to integrate Thought-Centric Preference Optimization (TCPO) into embodied decision-making by transforming sparse reward signals into richer step sample pairs.
Outcome: The proposed approach achieves an average success rate of 26.67% in the ALFWorld environment, and a 6% improvement over RL4VLM.
LLMsPark: A Benchmark for Evaluating Large Language Models in Strategic Gaming Contexts (2025.findings-emnlp)

Copied to clipboard

Challenge: Large language models (LLMs) are increasingly important for their intelligence evaluation.
Approach: They propose a game theory-based evaluation platform that measures LLMs’ decision-making strategies and social behaviors in classic game-theoretic settings.
Outcome: The proposed system cross-evaluates 15 leading LLMs using leaderboard rankings and scoring mechanisms.
Dual Dynamic Memory Network for End-to-End Multi-turn Task-oriented Dialog Systems (2020.coling-main)

Copied to clipboard

Challenge: Existing task-oriented dialog systems struggle to dynamically model long dialog context for interactions and effectively incorporate knowledge base (KB) information into dialog generation.
Approach: They propose a dual dynamic memory network for multi-turn dialog generation . the model dynamically expands the dialog memory turn by turn and keeps track of dialog history .
Outcome: The proposed model outperforms baseline models on three benchmark datasets on human evaluation and automatic evaluation.
OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems (2024.acl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) and Large Multimodal Models have exceeded general human capabilities in various tasks.
Approach: They present an Olympiad-level bilingual multimodal scientific benchmark featuring 8,476 problems from Olympiad level mathematics and physics competitions.
Outcome: The best performing model, GPT-4V, attains an average score of 17.97% on OlympiadBench, with a mere 10.74% in physics, highlighting the benchmark rigor and the intricacy of physical reasoning.
Handling Missing Entities in Zero-Shot Named Entity Recognition: Integrated Recall and Retrieval Augmentation (2025.naacl-long)

Copied to clipboard

Challenge: Zero-shot Named Entity Recognition (ZS-NER) aims to recognize entities in unseen domains without specific annotated data.
Approach: They propose a novel two-stage framework leveraging large language model techniques to improve the ZS-NER’s recall rate.
Outcome: The proposed framework improves the ZS-NER’s recall rate and accuracy by incorporating a large language model.
AgencyBench: Benchmarking the Frontiers of Autonomous Agents in 1M-Token Real-World Contexts (2026.acl-long)

Copied to clipboard

Challenge: Existing benchmarks focus on single agentic capability, failing to capture long-horizon real-world scenarios.
Approach: They propose a benchmark that evaluates 6 agentic capabilities across 32 real-world scenarios.
Outcome: Experiments show that closed-source models outperform open-source model (48.4% vs 32.1%) integrating models with advanced scaffolds to form autonomous agents is a paradigm shift.

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