Papers by Jiacheng Zhu

17 papers
Adaptive Spatial and Temporal Redundancy Optimization for Efficient Reasoning in Large Language Models (2026.acl-long)

Copied to clipboard

Challenge: Existing research to improve CoT efficiency falls into three categories, each with distinct limitations.
Approach: They propose a training-free framework that addresses both dimensions of CoT reasoning by applying a progressive precision reduction strategy coupled with an entropy-based confidence mechanism for adaptive termination.
Outcome: Empirical results show that the proposed framework achieves 11.3 efficiency gain without compromising accuracy.
TreeBoN: Enhancing Inference-Time Alignment with Speculative Tree-Search and Best-of-N Sampling (2025.findings-emnlp)

Copied to clipboard

Challenge: Best-of-N (BoN) sampling generates multiple responses and selects the best one, achieving improved performance but with a high computational cost.
Approach: They propose a framework that integrates a speculative tree-search strategy into Best-of-N (BoN) Sampling.
Outcome: The proposed framework outperforms Best-of-N (BoN) sampling but has high computational cost . tree-search strategy reduces computational overhead while maintaining high output quality .
AutoRAN: Automated Hijacking of Safety Reasoning in Large Reasoning Models (2026.acl-long)

Copied to clipboard

Challenge: Large reasoning models (LRMs) generate coherent reasoning paths before conclusions, but they introduce new vulnerabilities.
Approach: They propose a framework that leverages a weaker but less-aligned model to simulate execution reasoning for initial hijacking attempts and iteratively refines attacks by exploiting reasoning patterns leaked through the target LRM’s refusals.
Outcome: The proposed framework achieves 100% success rate within one or few turns, neutralizing reasoning-based defenses even when evaluated by robustly aligned external models.
BTC-LLM: Efficient Sub-1-Bit LLM Quantization via Learnable Transformation and Binary Codebook (2026.acl-long)

Copied to clipboard

Challenge: Recent sparsity-aware binarization approaches can achieve sub-1-bit compression, but they face performance degradation, mask-management overhead, and limited hardware compatibility.
Approach: They propose a binary quantization framework that leverages binary pattern clustering and weight transformation to overcome performance degradation and mask-management overhead.
Outcome: The proposed framework achieves state-of-the-art compression (1.11–0.7 bits) it maintains high performance with only a 3.1% accuracy drop in zero-shot benchmarks while delivering a 1.6 speedup over FP16.
BabyWalk: Going Farther in Vision-and-Language Navigation by Taking Baby Steps (2020.acl-main)

Copied to clipboard

Challenge: Existing state-of-the-art VLN agents do not generalize well for long navigation tasks.
Approach: They propose a VLN agent that is learned to navigate by decomposing long instructions into shorter ones and completing them sequentially.
Outcome: The proposed agent can follow long instructions better than existing ones, but it does not generalize well.
Bit-by-Bit: Progressive QAT Strategy with Outlier Channel Splitting for Stable Low-Bit LLMs (2026.acl-long)

Copied to clipboard

Challenge: Existing approaches to training LLMs at ultra-low precisions suffer from convergence instability and substantial training costs.
Approach: They propose a progressive QAT framework with outlier channel splitting to address these issues . they use nested structure of integer quantization grids to enable a "train once, deploy any precision" paradigm .
Outcome: The proposed framework outperforms baselines on both Llama2/3 and W2A16, with an 11 speedup over BF16.
SCCS: Semantics-Consistent Cross-domain Summarization via Optimal Transport Alignment (2023.findings-acl)

Copied to clipboard

Challenge: Existing methods for multimodal summarization ignore the structure and semantics of the whole video and article.
Approach: They propose a semantic-consistent cross-domain summarization model that extracts features from video and article and uses fusion methods to select representative one.
Outcome: The proposed model produces high-quality multimodal summaries on three MSMO datasets.
ICG: Improving Cover Image Generation via MLLM-based Prompting and Personalized Preference Alignment (2025.emnlp-main)

Copied to clipboard

Challenge: Large language models and diffusion models have opened new possibilities for AI-generated content . personalized cover image generation remains underexplored despite its critical role in boosting user engagement on digital platforms.
Approach: They propose a framework that integrates MLLM-based prompting with personalized preference alignment to generate high-quality, contextually relevant covers.
Outcome: The proposed framework improves image quality, semantic fidelity, and personalization, leading to stronger user appeal and offline recommendation accuracy in downstream tasks.
QaRL: Rollout-Aligned Quantization-Aware RL for Fast and Stable Training under Training–Inference Mismatch (2026.findings-acl)

Copied to clipboard

Challenge: Recent work has shown that reinforcement learning with simple rule-based reward functions (RLVR) can induce emergent reasoning behaviors and yield gains in challenging domains such as math problem solving.
Approach: They propose a rollout-alignment-quantization-aware RL which aligns training-side forward with the quantized rollout to minimize mismatch.
Outcome: The proposed approach outperforms quantized-rollout training by +5.5 on Qwen3-30B-A3B MoE for math problems while maintaining low-bit throughput.
Dynamic Data Mixing Maximizes Instruction Tuning for Mixture-of-Experts (2025.naacl-long)

Copied to clipboard

Challenge: Mixture-of-Experts (MoE) models are constrained by their fixed model capacities when the number of tasks grows in instruction tuning.
Approach: They propose to combine all training tasks and apply fixed sampling weights without considering the importance of different tasks as the model training state changes.
Outcome: The proposed method can be used on knowledge & reasoning tasks and open-ended queries with limited training budget.
MedEthicEval: Evaluating Large Language Models Based on Chinese Medical Ethics (2025.naacl-industry)

Copied to clipboard

Challenge: Large language models (LLMs) have been used in clinical decision support, medical education and patient communication.
Approach: They propose a benchmark to evaluate large language models in the domain of medical ethics and assess their grasp of medical ethical principles and their application across diverse scenarios.
Outcome: The proposed framework assesses the models’ grasp of medical ethics principles and their ability to apply them across diverse scenarios.
LLaMA-MoE: Building Mixture-of-Experts from LLaMA with Continual Pre-Training (2024.emnlp-main)

Copied to clipboard

Challenge: Mixture-of-Experts (MoE) has gained increasing popularity as a framework for scaling up large language models.
Approach: They investigate how to build Mixture-of-Experts (MoE) models from existing large language models . they use expert construction, Continual pre-training and data sampling strategies .
Outcome: The proposed model outperforms existing models with similar parameters on a wide range of tasks.
StyleDistance: Stronger Content-Independent Style Embeddings with Synthetic Parallel Examples (2025.naacl-long)

Copied to clipboard

Challenge: Existing methods for embedding text are limited by the imperfect nature of data acquired under such assumptions.
Approach: They propose a new approach to training stronger content-independent style embeddings using a synthetic dataset of near-exact paraphrases with controlled style variations.
Outcome: The proposed model outperforms existing methods in real-world benchmarks and outperformed leading style representations in downstream applications.
mStyleDistance: Multilingual Style Embeddings and their Evaluation (2025.findings-acl)

Copied to clipboard

Challenge: Multilingual StyleDistance embeddings are useful for stylistic analysis and style transfer, but they only exist for English.
Approach: They propose a method that can generate style embeddings in new languages using synthetic data and a contrastive loss.
Outcome: The proposed method outperforms existing style embeddings on these benchmarks and generalizes well to unseen features and languages.
Transfer Knowledge from Natural Language to Electrocardiography: Can We Detect Cardiovascular Disease Through Language Models? (2023.findings-eacl)

Copied to clipboard

Challenge: Recent advances in Large Language Models (LLMs) have shown powerful ability in various downstream applications.
Approach: They propose an approach for cardiovascular disease diagnosis and automatic ECG diagnosis report generation.
Outcome: The proposed approach generates high-quality cardiac diagnosis reports and achieves competitive zero-shot classification performance even compared with supervised baselines.
TextFlint: Unified Multilingual Robustness Evaluation Toolkit for Natural Language Processing (2021.acl-demo)

Copied to clipboard

Challenge: Existing approaches to textual robustness evaluation focus on slightly modifying the input data, which maintains the original meaning and results in a different prediction.
Approach: They propose a multilingual robustness evaluation toolkit for NLP that integrates universal text transformations, task-specific transformations and adversarial attack.
Outcome: The toolkit includes universal text transformation, task-specific transformation, adversarial attack, subpopulation, and their combinations to provide comprehensive robustness analyses.
Can Brain Signals Reveal Inner Alignment with Human Languages? (2023.findings-emnlp)

Copied to clipboard

Challenge: Brain Signals, such as Electroencephalography, and human languages have been explored independently for many downstream tasks, however, the connection between them has not been well explored.
Approach: They introduce a multimodal transformer alignment model to observe coordinated representations between EEG and language.
Outcome: The proposed method achieved an F1-score improvement of 1.7% on ZuCo and 9.3% on Zuco datasets for sentiment analysis, and 7.4% on ZuCO for relation detection.

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