29 papers
Coupled Harness--Model Evolution for Scientific Equation Discovery
Pengze Li, Jiaquan Zhang, Encheng Su +8
Large language models (LLMs) are increasingly used to discover scientific equations from experimental data. Such a discovery system has two parts that must work together: a library…
Context-Aware Cluster Decoding: Semantic Anchor-Driven Coherence in dMLLMs
Yikai Zhao, Qiyan Zhao, Jiaquan Zhang +3
Diffusion multimodal large language models (dMLLMs) frequently produce long-form outputs marred by semantic drift and repetition, with quality generally degrading as output length…
Geometry-aware Incremental Neural Operator for Long-Horizon PDE prediction
Jiaquan Zhang, Shuxu Chen, Haifan Meng +6
Neural operators have shown strong potential for learning solution operators of partial differential equations (PDEs). However, long-horizon autoregressive prediction remains chall…
HERO: History-Enriched Rollout Training for Long-Horizon Autoregressive Neural Operators
Jiaquan Zhang, Shuxu Chen, Haifan Meng +6
Neural operators provide fast surrogates for time-dependent partial differential equations (PDEs) by applying a learned evolution operator recursively to its own predictions, but t…
TF-SNO: Time-Frequency Gated Spectral Neural Operators for Learning Non-Stationary Partial Differential Equations
Yitian Zhou, Chaoning Zhang, Zhenzhen Huang +8
Non-stationary partial differential equations (PDEs) arise throughout scientific computing, where the dominant frequency content and energy distribution can drift over time. While…
Autoregression-Free Neural Operators for Time-Dependent PDEs
Jiaquan Zhang, Caiyan Qin, Haoyu Bian +7
Neural operators learn mappings from function-dependent inputs to solutions, providing an effective framework for solving partial differential equations (PDEs). For time-dependent…
Efficient RAG with Intent-Aware Retrieval and Semantics-Preserving Chunking
Fachrina Dewi Puspitasari, Chaoning Zhang, Jiaquan Zhang +6
The demand for powerful instruction following and reasoning capability of large language models (LLMs) has promoted rapid development of retrieval-augmented generation (RAG). The R…
From Similarity to Structure: Training-free LLM Context Compression with Hybrid Graph Priors
Yitian Zhou, Chaoning Zhang, Jiaquan Zhang +6
Long-context large language models remain computationally expensive to run and often fail to reliably process very long inputs, which makes context compression an important compone…
Small Language Model Helps Resolve Semantic Ambiguity of LLM Prompt
Zhenzhen Huang, Chaoning Zhang, Fachrina Dewi Puspitasari +4
Large language models (LLMs) are increasingly utilized in various complex reasoning tasks due to their excellent instruction following capability. However, the model's performance…
Lightweight LLM Agent Memory with Small Language Models
Jiaquan Zhang, Chaoning Zhang, Shuxu Chen +9
Although LLM agents can leverage tools for complex tasks, they still need memory to maintain cross-turn consistency and accumulate reusable information in long-horizon interactions…
Weak-Link Optimization for Multi-Agent Reasoning and Collaboration
Haoyu Bian, Chaoning Zhang, Jiaquan Zhang +4
LLM-driven multi-agent frameworks address complex reasoning tasks through multi-role collaboration. However, existing approaches often suffer from reasoning instability, where indi…
Agent-GWO: Collaborative Agents for Dynamic Prompt Optimization in Large Language Models
Xudong Wang, Chaoning Zhang, Chenghao Li +10
Large Language Models (LLMs) have demonstrated strong capabilities in complex reasoning tasks, while recent prompting strategies such as Chain-of-Thought (CoT) have further elevate…
Bias Redistribution in Visual Machine Unlearning: Does Forgetting One Group Harm Another?
Yunusa Haruna, Adamu Lawan, Ibrahim Haruna Abdulhamid +4
Machine unlearning enables models to selectively forget training data, driven by privacy regulations such as GDPR and CCPA. However, its fairness implications remain underexplored:…
CAP-CoT: Cycle Adversarial Prompt for Improving Chain of Thoughts in LLM Reasoning
Shuxu Chen, Yitian Zhou, Jiaquan Zhang +6
Chain-of-Thought (CoT) prompting has emerged as a simple and effective way to elicit step-by-step solutions from large language models (LLMs). However, CoT reasoning can be unstabl…
Topology-Aware Layer Pruning for Large Vision-Language Models
Pengcheng Zheng, Chaoning Zhang, Ya Wen +10
Large Language Models (LLMs) have demonstrated strong capabilities in natural language understanding and reasoning, while recent extensions that incorporate visual inputs enable th…
TDA-RC: Task-Driven Alignment for Knowledge-Based Reasoning Chains in Large Language Models
Jiaquan Zhang, Qigan Sun, Chaoning Zhang +11
Enhancing the reasoning capability of large language models (LLMs) remains a core challenge in natural language processing. The Chain-of-Thought (CoT) paradigm dominates practical…
Efficient and Interpretable Multi-Agent LLM Routing via Ant Colony Optimization
Xudong Wang, Chaoning Zhang, Jiaquan Zhang +8
Large Language Model (LLM)-driven Multi-Agent Systems (MAS) have demonstrated strong capability in complex reasoning and tool use, and heterogeneous agent pools further broaden the…
AI-for-Science Low-code Platform with Bayesian Adversarial Multi-Agent Framework
Zihang Zeng, Jiaquan Zhang, Pengze Li +2
Large Language Models (LLMs) demonstrate potentials for automating scientific code generation but face challenges in reliability, error propagation in multi-agent workflows, and ev…
Learning Global Hypothesis Space for Enhancing Synergistic Reasoning Chain
Jiaquan Zhang, Chaoning Zhang, Shuxu Chen +9
Chain-of-Thought (CoT) has been shown to significantly improve the reasoning accuracy of large language models (LLMs) on complex tasks. However, due to the autoregressive, step-by-…
Optimizing Soft Prompt Tuning via Structural Evolution
Zhenzhen Huang, Chaoning Zhang, Haoyu Bian +8
Soft prompt tuning leverages continuous embeddings to capture task-specific information in large pre-trained language models (LLMs), achieving competitive performance in few-shot s…
Geometric Neural Operators via Lie Group-Constrained Latent Dynamics
Jiaquan Zhang, Fachrina Dewi Puspitasari, Songbo Zhang +7
Neural operators offer an effective framework for learning solutions of partial differential equations for many physical systems in a resolution-invariant and data-driven manner. E…
Rethinking Input Domains in Physics-Informed Neural Networks via Geometric Compactification Mappings
Zhenzhen Huang, Haoyu Bian, Jiaquan Zhang +6
Several complex physical systems are governed by multi-scale partial differential equations (PDEs) that exhibit both smooth low-frequency components and localized high-frequency st…
Text summarization via global structure awareness
Jiaquan Zhang, Chaoning Zhang, Shuxu Chen +9
Text summarization is a fundamental task in natural language processing (NLP), and the information explosion has made long-document processing increasingly demanding, making summar…
LLaVA-FA: Learning Fourier Approximation for Compressing Large Multimodal Models
Pengcheng Zheng, Chaoning Zhang, Jiarong Mo +8
Large multimodal models (LMMs) have achieved impressive performance on various vision-language tasks, but their substantial computational and memory costs hinder their practical de…