Papers by Zhang Yueyang

10 papers
L2Dir: Integrating L_2-Norm and Directional Alignment for Unsupervised Contrastive Representation Learning in Multimodal Retrieval (2026.acl-long)

Copied to clipboard

Challenge: Existing approaches to multimodal representation learning focus on directional alignment and embedding magnitudes (L2-norm) however, these methods often fail to account for the intrinsic role of L2-norm in the contrastive process.
Approach: They propose a plug-and-play framework that optimizes L2-norm alignment and Directional consistency jointly.
Outcome: The proposed framework achieves consistent and significant performance gains over established baselines across 95 tasks using UniIR and VLM2Vec-V2 frameworks.
Graph-GRPO: Stabilizing Multi-Agent Topology Learning via Group Relative Policy Optimization (2026.findings-acl)

Copied to clipboard

Challenge: Recent approaches to optimize communication topology rely on single-sample policy gradients with absolute rewards.
Approach: They propose a topology optimization framework that integrates Group Relative Policy Optimization.
Outcome: The proposed topology optimization framework outperforms state-of-the-art methods on reasoning and code generation benchmarks.
Distilling Large Embeddings via Hyperspherical Householder Quantization (2026.acl-long)

Copied to clipboard

Challenge: Existing methods for quantizing large embeddings rely on Euclidean quantization, which is poorly aligned with the angular geometry induced by contrastive embeddment training.
Approach: They propose a geometry-aware distillation method that compresses large embeddings into short discrete representations via iterative Householder transformations on the unit hypersphere.
Outcome: The proposed method reduces decoding cost and maintains strong semantic retrieval accuracy.
CLEAN–EVAL: Clean Evaluation on Contaminated Large Language Models (2024.findings-naacl)

Copied to clipboard

Challenge: Existing methods to evaluate large language models are prone to data contamination.
Approach: They propose a method which parses contaminated data and back-translates it into a candidate set.
Outcome: The proposed method reduces data contamination and evaluates the LLMs more cleanly.
LNE-Blocking: An Efficient Framework for Contamination Mitigation Evaluation on Large Language Models (2025.findings-emnlp)

Copied to clipboard

Challenge: a problem of data contamination is now almost inevitable during the development of large language models, with the training data often integrating evaluation benchmarks even unintentionally.
Approach: They propose a framework to restore model performance prior to data contamination on potentially leaked datasets by using contamination detection and disruption operation.
Outcome: The proposed framework restores model performance prior to contamination on potentially leaked datasets.
DINT Transformer (2025.emnlp-main)

Copied to clipboard

Challenge: Experimental results show that the DINT Transformer improves accuracy and robustness across practical applications.
Approach: They propose a differential attention mechanism that suppresses the impact of irrelevant contexts by computing DIF-Ference between two independent attention distributions.
Outcome: The proposed architecture improves numerical stability and ability to capture global dependencies.
ReflectRM: Boosting Generative Reward Models via Self-Reflection within a Unified Judgment Framework (2026.acl-long)

Copied to clipboard

Challenge: Existing methods for generating reward models focus on outcome-level supervision, neglecting analytical process quality, which constrains their potential.
Approach: They propose a novel reward model that leverages self-reflection to assess analytical quality and enhance preference modeling.
Outcome: The proposed model improves performance on four benchmarks and significantly mitigates positional bias.
ConsistRM: Improving Generative Reward Models via Consistency-Aware Self-Training (2026.acl-long)

Copied to clipboard

Challenge: ConsistRM is a self-training framework that enables effective and stable GRM training without human annotations.
Approach: They propose a self-training framework that enables effective and stable GRM training without human annotations.
Outcome: The proposed framework outperforms vanilla Reinforcement Fine-Tuning (RFT) by 1.5% on five benchmark datasets.
TPLinker: Single-stage Joint Extraction of Entities and Relations Through Token Pair Linking (2020.coling-main)

Copied to clipboard

Challenge: Existing methods to extract entities and relations from unstructured text are susceptible to cascading errors due to the separation of entity detection and relation classification.
Approach: They propose a one-stage joint extraction model that detects overlapping relations while being immune from exposure bias.
Outcome: The proposed model can identify overlapping relations while being immune from exposure bias.
LLaTiSA: Towards Difficulty-Stratified Time Series Reasoning from Visual Perception to Semantics (2026.findings-acl)

Copied to clipboard

Challenge: Current research hinders the development of unified Time Series Reasoning Models (TSRMs) time series data are a fundamental modality for capturing the temporal dynamics of complex systems.
Approach: They propose a time series reasoning model that integrates visualized patterns with precision-calibrated numerical tables to enhance the temporal perception of Vision-Language Models.
Outcome: The proposed model outperforms existing models and exhibits robust out-of-distribution generalization across diverse tasks and real-world scenarios.

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