Papers by Wenhu Zhang

13 papers
E2-LLM: Efficient and Extreme Length Extension of Large Language Models (2024.findings-acl)

Copied to clipboard

Challenge: Existing techniques for extending context capabilities in LLMs require additional training procedures and access to datasets with long context (e.g., sequences of 32K tokens).
Approach: They propose a solution to extend context capabilities in Large Language Models by training a single process over a sequence of 4K tokens.
Outcome: The proposed solution significantly reduces the cost of continual-pretraining or fine-tuning over short sequences and improves robustness to diverse relative positions.
Generative Bridging Network for Neural Sequence Prediction (N18-1)

Copied to clipboard

Challenge: Existing approaches to improve the likelihood of sequence prediction models are based on MLE and teacher forcing.
Approach: They propose a Generative Bridging Network (GBN) that extends the point-wise ground truth to a bridge distribution conditioned on it and optimizes their KL-divergence.
Outcome: The proposed bridge module can improve on two recognized sequence prediction tasks and minimize learning burden.
MusiLingo: Bridging Music and Text with Pre-trained Language Models for Music Captioning and Query Response (2024.findings-naacl)

Copied to clipboard

Challenge: Large Language Models have shown immense potential in multimodal applications, but convergence between textual and musical domains remains unexplored.
Approach: They propose a system that aligns music representations with a frozen LLM . they train the system on an extensive music caption dataset and fine-tune it with instructional data .
Outcome: The proposed system bridges the gap between music audio and textual contexts by combining music captions with a frozen model . it performs well in generating music caption and composing music-related Q&A pairs . the proposed system is available for free download at http://www.musilingo.com/ .
VideoScore: Building Automatic Metrics to Simulate Fine-grained Human Feedback for Video Generation (2024.emnlp-main)

Copied to clipboard

Challenge: Existing video metrics are lagging behind in providing reliable scores over generated videos due to lack of large-scale human-annotated dataset.
Approach: They propose to use VideoFeedback to train a human-annotated multi-aspect score over 37.6K synthesized videos from 11 existing video generative models.
Outcome: The proposed model outperforms the prior best metrics by 50 points in the test.
SWE-QA-Pro: A Representative Benchmark and Scalable Training Recipe for Repository-Level Code Understanding (2026.findings-acl)

Copied to clipboard

Challenge: Existing benchmarks for agentic repository-level code understanding overlook long tail topics and rely on memorized knowledge.
Approach: They propose a repository-level agentic code understanding benchmark that uses long-tail repositories with executable environments to enforce topical balance.
Outcome: Empirically, a Qwen3-8B model trained with the proposed benchmark outperforms GPT-4o by 2.3 points.
ChatMusician: Understanding and Generating Music Intrinsically with LLM (2024.findings-acl)

Copied to clipboard

Challenge: Despite LLMs' impressive capabilities in musical knowledge, music reasoning remains an unsolved task.
Approach: They propose an open-source large language model (LLM) that integrates intrinsic musical abilities into LLaMA2 and GPT-3.5.
Outcome: The proposed model can understand and generate music with a pure text tokenizer without external multi-modal neural structures or tokenizers.
MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark (2025.acl-long)

Copied to clipboard

Challenge: Recent advances in multimodal large language models have led to progress in tackling complex reasoning tasks that combine textual and visual information.
Approach: They introduce a robust version of the Massive Multi-discipline Multimodal Understanding and Reasoning (MMMU) benchmark.
Outcome: The proposed model performs lower on MMMU-Pro than on the previous benchmark, ranging from 16.8% to 26.9%.
SearchGym: Bootstrapping Real-World Search Agents via Cost-Effective and High-Fidelity Environment Simulation (2026.acl-long)

Copied to clipboard

Challenge: Search agents are a pivotal paradigm for solving open-ended, knowledge-intensive reasoning tasks.
Approach: They propose a search agent simulation environment that bootstraps robust search agents using Reinforcement Learning.
Outcome: The proposed model outperforms the web-enhanced ASearcher model by 10.6%.
TRAC: Teacher-Guided Token Reward with Adaptive Calibration for Robust Policy Optimization (2026.acl-long)

Copied to clipboard

Challenge: Current reward models for reinforcement learning (RL) rely on outcome rewards that propagate a single scalar value across all tokens based on final correctness.
Approach: They propose a framework that derives dense token-level supervision from LLMs . they use a multi-granularity calibration mechanism to modulate teacher influence .
Outcome: The proposed framework evaluates teacher reliability across problem-level expertise, trajectory-level discrimination, and token-level confidence.
BrowseComp-Plus: A Fair and Disentangled Evaluation Benchmark for Deep Search Agents (2026.acl-long)

Copied to clipboard

Challenge: Existing benchmarks for deep search agents rely on blackbox web search APIs . dynamic and opaque web APIs hinder reproducibility and fair comparisons - authors .
Approach: They propose a benchmark that employs a fixed corpus for controlled retrieval for deep search agents.
Outcome: The new benchmark shows that agents that combine large language models with retrieval tools excel at complex, reasoning-intensive queries.
SciMMIR: Benchmarking Scientific Multi-modal Information Retrieval (2024.findings-acl)

Copied to clipboard

Challenge: Multi-modal information retrieval (MMIR) is a rapidly evolving field . current benchmarks for image-text pairings overlook the scientific domain .
Approach: They develop a scientific domain-specific MMIR benchmark to evaluate image-text pairings using open-access research paper corpora.
Outcome: The proposed benchmarks are based on 530K image-text pairs extracted from scientific documents with detailed captions.
Logic2Text: High-Fidelity Natural Language Generation from Logical Forms (2020.findings-emnlp)

Copied to clipboard

Challenge: Recent studies on Natural Language Generation (NLG) from structured data focus on surface descriptions of simple record sequences, for example, attribute-value pairs of fixed or very limited schema.
Approach: They propose to use a large-scale dataset to generate NLG from logical forms to obtain controllable and faithful generations from structured data.
Outcome: The proposed model can describe interesting facts from logical inferences across records, but it is difficult to produce such fidelity.
OpenCodeInterpreter: Integrating Code Generation with Execution and Refinement (2024.findings-acl)

Copied to clipboard

Challenge: OpenCodeInterpreter-33B provides a high level of performance for code generation, executing, and iterative refinement.
Approach: They propose a family of open-source code systems for generating, executing, and iteratively refining code.
Outcome: The OpenCodeInterpreter-33B performs well on humanEval, MBPP, and EvalPlus benchmarks.

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