Publications (63)
h-MINT: Modeling Pocket-Ligand Binding with Hierarchical Molecular Interaction Network
Yanru Qu, Yijie Zhang, Wenjuan Tan +6
Accurate molecular representations are critical for drug discovery, and a central challenge lies in capturing the chemical environment of molecular fragments, as key interactions,…
ElasticMem: Latent Memory as a Learnable Resource for LLM Agents
Tao Feng, Chongrui Ye, Tianyang Luo +5
Long-term memory is essential for LLM agents to reason coherently across extended interactions, personalize responses, and reuse past experience. However, existing memory-augmented…
Steer2Adapt: Dynamically Composing Steering Vectors Elicits Efficient Adaptation of LLMs
Pengrui Han, Xueqiang Xu, Keyang Xuan +12
Activation steering has emerged as a promising approach for efficiently adapting large language models (LLMs) to downstream behaviors. However, most existing steering methods rely…
Neural PM: A Long-Range Interaction Modeling Enhancer for Geometric GNNs
Yusong Wang, Chaoran Cheng, Shaoning Li +5
Geometric graph neural networks (GNNs) have emerged as powerful tools for modeling molecular geometry. However, they encounter limitations in effectively capturing long-range inter…
Lightweight MSA Design Advances Protein Folding From Evolutionary Embeddings
Hanqun Cao, Xinyi Zhou, Zijun Gao +7
Protein structure prediction often hinges on multiple sequence alignments (MSAs), which underperform on low-homology and orphan proteins. We introduce PLAME, a lightweight MSA desi…
Fine-tuning Flow Matching Generative Models with Intermediate Feedback
Jiajun Fan, Chaoran Cheng, Shuaike Shen +2
Flow-based generative models have shown remarkable success in text-to-image generation, yet fine-tuning them with intermediate feedback remains challenging, especially for continuo…
Reinforcement Learning with Evolving Rubrics as Rewards for Audio Reasoning
Fangxu Yu, Tao Feng, Dehai Min +6
Audio reasoning is essential for machine understanding of the acoustic world. Reinforcement learning with verifiable rewards can elicit such reasoning, yet existing reward designs…
The Many Faces of On-Policy Distillation: Pitfalls, Mechanisms, and Fixes
Siqi Zhu, Xuyan Ye, Hongyu Lu +2
On-policy distillation (OPD) and on-policy self-distillation (OPSD) have emerged as promising post-training methods for large language models, offering dense token-level supervisio…
Data Efficient Training for Reinforcement Learning with Adaptive Behavior Policy Sharing
Ge Liu, Rui Wu, Heng-Tze Cheng +7
Deep Reinforcement Learning (RL) is proven powerful for decision making in simulated environments. However, training deep RL model is challenging in real world applications such as…
FARM: Enhancing Molecular Representations with Functional Group Awareness
Thao Nguyen, Kuan-Hao Huang, Ge Liu +3
We introduce Functional Group-Aware Representations for Small Molecules (FARM), a novel foundation model designed to bridge the gap between SMILES, natural language, and molecular…
Maximizing Overall Diversity for Improved Uncertainty Estimates in Deep Ensembles
Siddhartha Jain, Ge Liu, Jonas Mueller +1
The inaccuracy of neural network models on inputs that do not stem from the training data distribution is both problematic and at times unrecognized. Model uncertainty estimation c…
Hierarchical protein backbone generation with latent and structure diffusion
Jason Yim, Marouane Jaakik, Ge Liu +5
We propose a hierarchical protein backbone generative model that separates coarse and fine-grained details. Our approach called LSD consists of two stages: sampling latents which a…
Generative Modeling of Discrete Latent Structures via Dynamic Policy Gradients
Stefan Ivanovic, Ge Liu, Mohammed El-Kebir
Many scientific problems require inferring unobserved mechanistic latent states from indirect observations. While classical approaches, including expectation maximization, do not s…
LangFlow: Continuous Diffusion Rivals Discrete in Language Modeling
Yuxin Chen, Chumeng Liang, Hangke Sui +4
Continuous diffusion has been the foundation of high-fidelity, controllable, and few-step generation of many data modalities such as images. However, in language modeling, prior co…
Auto-Dreamer: Learning Offline Memory Consolidation for Language Agents
Chongrui Ye, Yuxiang Liu, Yu Wang +5
Language agents increasingly operate over streams of related tasks, yet existing memory systems struggle to convert accumulated experience into reusable knowledge. Retrieval-augmen…
Thought-Retriever: Don't Just Retrieve Raw Data, Retrieve Thoughts for Memory-Augmented Agentic Systems
Tao Feng, Pengrui Han, Guanyu Lin +2
Large language models (LLMs) have transformed AI research thanks to their powerful internal capabilities and knowledge. However, existing LLMs still fail to effectively incorporate…
Position: The Hidden Costs and Measurement Gaps of Reinforcement Learning with Verifiable Rewards
Fang Wu, Aaron Tu, Weihao Xuan +21
Reinforcement learning with verifiable rewards (RLVR) is a practical, scalable way to improve large language models on math, code, and other structured tasks. However, we argue tha…
Protein Autoregressive Modeling via Multiscale Structure Generation
Yanru Qu, Cheng-Yen Hsieh, Zaixiang Zheng +2
We present protein autoregressive modeling (PAR), the first multi-scale autoregressive framework for protein backbone generation via coarse-to-fine next-scale prediction. Using the…
Constraint-First Reasoning: A Training-Free Protocol for Exploiting Answer-Space Constraints in Mathematical Problem Solving
Hongbo Ma, Bangji Yang, Yunqian Selina Cheng +3
Large language models can derive a plausible mathematical object yet still violate explicit requirements--for example, by omitting a modular reduction, returning a non-integer, or…
A-CODE: Fully Atomic Protein Co-Design with Unified Multimodal Diffusion
Chaoran Cheng, Jiaqi Guan, Milong Ren +5
We present A-CODE, a fully atomic unified one-stage protein co-design model that simultaneously refines discrete atom types and continuous atom coordinates. Unlike predominant two-…
M3: High-fidelity Text-to-Image Generation via Multi-Modal, Multi-Agent and Multi-Round Visual Reasoning
Bangji Yang, Ruihan Guo, Jiajun Fan +2
Generative models have achieved impressive fidelity in text-to-image synthesis, yet struggle with complex compositional prompts involving multiple constraints. We introduce \textbf…
LLMRouter: Unified Infrastructure for Developing, Evaluating, and Deploying LLM Routers
Tao Feng, Fangxu Yu, Haozhen Zhang +9
No single large language model (LLM) is optimal across all queries and budget constraints, making model routing essential for cost-effective deployment. Existing routers adopt dive…
ProteinZero: Self-Improving Protein Generation via Online Reinforcement Learning
Ziwen Wang, Jiajun Fan, Ruihan Guo +3
Protein generative models have shown remarkable promise in protein design, yet their success rates remain constrained by reliance on curated sequence-structure datasets and by misa…
Information Condensing Active Learning
Siddhartha Jain, Ge Liu, David Gifford
We introduce Information Condensing Active Learning (ICAL), a batch mode model agnostic Active Learning (AL) method targeted at Deep Bayesian Active Learning that focuses on acquir…
From Supervision to Exploration: What Does Protein Language Model Learn During Reinforcement Learning?
Hanqun Cao, Hongrui Zhang, Junde Xu +12
Protein language models (PLMs) have advanced computational protein science through large-scale pretraining and scalable architectures. In parallel, reinforcement learning (RL) has…
Pessimistic Off-Policy Multi-Objective Optimization
Shima Alizadeh, Aniruddha Bhargava, Karthick Gopalswamy +3
Multi-objective optimization is a type of decision making problems where multiple conflicting objectives are optimized. We study offline optimization of multi-objective policies fr…
SF-Cluster: Frustration-Guided MSA Subsampling for Alternative Protein Conformation Recovery
Hanqun Cao, Zijun Gao, Chunbin Gu +3
Deep-learning structure predictors are sensitive to their multiple sequence alignment (MSA) input, making MSA subsampling a practical route to recovering alternative conformations.…
Online Reward-Weighted Fine-Tuning of Flow Matching with Wasserstein Regularization
Jiajun Fan, Shuaike Shen, Chaoran Cheng +3
Recent advancements in reinforcement learning (RL) have achieved great success in fine-tuning diffusion-based generative models. However, fine-tuning continuous flow-based generati…
Geometric Point Attention Transformer for 3D Shape Reassembly
Jiahan Li, Chaoran Cheng, Jianzhu Ma +1
Shape assembly, which aims to reassemble separate parts into a complete object, has gained significant interest in recent years. Existing methods primarily rely on networks to pred…
Retrieval is Cheap, Show Me the Code: Executable Multi-Hop Reasoning for Retrieval-Augmented Generation
Jiashuo Sun, Jimeng Shi, Yixuan Xie +10
Retrieval-Augmented Generation (RAG) has become a standard approach for knowledge-intensive question answering, but existing systems remain brittle on multi-hop questions, where so…
RouteProfile: Graph-Based Profiling for Cold-Start LLM Routing
Jingjun Xu, Hongji Pu, Tao Feng +3
LLM routing is increasingly important for selecting suitable models under diverse user needs and deployment constraints, but its practical effectiveness depends on continual adapta…
UniRec: Unified Multimodal Encoding for LLM-Based Recommendations
Zijie Lei, Tao Feng, Zhigang Hua +5
Large language models have recently shown promise for multimodal recommendation, particularly with text and image inputs. Yet real-world recommendation signals extend far beyond th…
mCLM: A Modular Chemical Language Model that Generates Functional and Makeable Molecules
Carl Edwards, Chi Han, Gawon Lee +11
Despite their ability to understand chemical knowledge, large language models (LLMs) remain limited in their capacity to propose novel molecules with desired functions (e.g., drug-…
Categorical Flow Matching on Statistical Manifolds
Chaoran Cheng, Jiahan Li, Jian Peng +1
We introduce Statistical Flow Matching (SFM), a novel and mathematically rigorous flow-matching framework on the manifold of parameterized probability measures inspired by the resu…
Optimal Design for Human Preference Elicitation
Subhojyoti Mukherjee, Anusha Lalitha, Kousha Kalantari +4
Learning of preference models from human feedback has been central to recent advances in artificial intelligence. Motivated by the cost of obtaining high-quality human annotations,…
Improving Protein Sequence Design through Designability Preference Optimization
Fanglei Xue, Andrew Kubaney, Zhichun Guo +4
Protein sequence design methods have demonstrated strong performance in sequence generation for de novo protein design. However, as the training objective was sequence recovery, it…
Rethinking the Reranker: Boundary-Aware Evidence Selection for Robust Retrieval-Augmented Generation
Jiashuo Sun, Pengcheng Jiang, Saizhuo Wang +13
Retrieval-Augmented Generation (RAG) systems remain brittle under realistic retrieval noise, even when the required evidence appears in the top-K results. A key reason is that retr…
Experimental Design for Active Transductive Inference in Large Language Models
Subhojyoti Mukherjee, Anusha Lalitha, Aniket Deshmukh +3
One emergent ability of large language models (LLMs) is that query-specific examples can be included in the prompt at inference time. In this work, we use active learning for adapt…
Flow Matching Meets Biology and Life Science: A Survey
Zihao Li, Zhichen Zeng, Xiao Lin +9
Over the past decade, advances in generative modeling, such as generative adversarial networks, masked autoencoders, and diffusion models, have significantly transformed biological…
Multi-party quantum privacy comparison of size based on d-level GHZ states
Hao Cao, Wenping Ma, Liangdong Lyu +2
Quantum privacy comparison(QPC) plays an important role in secret ballot elections, private auctions and so on. To date, many multi-party QPC(MQPC) protocols have been proposed to…
Off-Policy Evaluation from Logged Human Feedback
Aniruddha Bhargava, Lalit Jain, Branislav Kveton +2
Learning from human feedback has been central to recent advances in artificial intelligence and machine learning. Since the collection of human feedback is costly, a natural questi…
EventConnector: Mining Social Event Relations through Temporal Graphs
Zijie Lei, Haofei Yu, Ge Liu +1
Understanding and retrieving related real-world events based on their temporal dynamics is a fundamental challenge in time-sensitive applications such as forecasting, information r…
ExpGraph: Model-Agnostic Experience Learning with Graph-Structured Memory for LLM Agents
Tao Feng, Chongrui Ye, Tianyang Luo +8
Large language model (LLM) agents have shown strong capabilities in reasoning, tool use, and multi-step interaction, but they often solve tasks from scratch and fail to reuse succe…
Adaptive Divergence Regularized Policy Optimization for Fine-tuning Generative Models
Jiajun Fan, Tong Wei, Chaoran Cheng +2
Balancing exploration and exploitation during reinforcement learning fine-tuning of generative models presents a critical challenge, as existing approaches rely on fixed divergence…
RSeg: Training-Free OOD Medical Tumor Segmentation via Anatomical Reasoning and Statistical Rejection
Shuaike Shen, Ke Liu, Jiaqing Xie +5
Foundation models for medical image segmentation struggle under out-of-distribution (OOD) shifts, often producing fragmented false positives on OOD tumors. We introduce RSeg,…
ExpWeaver: LLM Agents Learn from Experience via Latent RAG
Tao Feng, Tianyang Luo, Jingjun Xu +5
Experience learning has achieved promising results in enhancing LLM agent planning and reasoning by integrating past interactions as reusable knowledge. However, existing methods r…
Further Investigation on Classical Multiparty computation using Quantum Resources
Hao Cao, Wenping Ma, Ge Liu +1
The tremendous development of cloud computing and network technology makes it possible for multiple people with limited resources to complete a large-scale computing with the help…
Variable-Length Generative Protein Design via Generalized Poisson Flow
Chaoran Cheng, Zhanghan Ni, Yanru Qu +4
The ability to generate variable-length proteins is crucial in protein design, where the optimal length is often unknown and tightly coupled to designability. Current diffusion- an…
Training Free Guided Flow Matching with Optimal Control
Luran Wang, Chaoran Cheng, Yizhen Liao +2
Controlled generation with pre-trained Diffusion and Flow Matching models has vast applications. One strategy for guiding ODE-based generative models is through optimizing a target…
Riemannian Consistency Model
Chaoran Cheng, Yusong Wang, Yuxin Chen +3
Consistency models are a class of generative models that enable few-step generation for diffusion and flow matching models. While consistency models have achieved promising results…
MemReward: Graph-Based Experience Memory for LLM Reward Prediction with Limited Labels
Tianyang Luo, Tao Feng, Zhigang Hua +4
Reinforcement learning has emerged as a powerful paradigm for improving large language model (LLM) reasoning, where rollouts are sampled from the policy and reward signals computed…
LRanker: LLM Ranker for Massive Candidates
Tao Feng, Zijie Lei, Zhigang Hua +4
Large language models (LLMs) have recently shown strong potential for ranking by capturing semantic relevance and adapting across diverse domains, yet existing methods remain const…
-Flow: A Unified Framework for Continuous-State Discrete Flow Matching Models
Chaoran Cheng, Jiahan Li, Jiajun Fan +1
Recent efforts have extended the flow-matching framework to discrete generative modeling. One strand of models directly works with the continuous probabilities instead of discrete…
Paper Copilot: A Self-Evolving and Efficient LLM System for Personalized Academic Assistance
Guanyu Lin, Tao Feng, Pengrui Han +2
As scientific research proliferates, researchers face the daunting task of navigating and reading vast amounts of literature. Existing solutions, such as document QA, fail to provi…
SMART: LLM-Augmented Hybrid Retrieval for Dynamic Product Ads
Congfei Zhang, Jingxiao Ma, Xiaodong Liu +14
Dynamic Product Ads (DPA) require retrieving relevant items from multi-million product catalogs, balancing two competing objectives: retargeting (re-surfacing known interests) and…
Variational Supervised Contrastive Learning
Ziwen Wang, Jiajun Fan, Thao Nguyen +2
Contrastive learning has proven to be highly efficient and adaptable in shaping representation spaces across diverse modalities by pulling similar samples together and pushing diss…
Maximum n-times Coverage for Vaccine Design
Ge Liu, Alexander Dimitrakakis, Brandon Carter +1
We introduce the maximum -times coverage problem that selects overlays to maximize the summed coverage of weighted elements, where each element must be covered at least …
TSRouter: Dynamic Modality-Model Selection for Time Series Reasoning
Fangxu Yu, Tao Feng, Dehai Min +3
Time series reasoning is essential for real-world problem-solving. While both Large Language Models (LLMs) and Vision-Language Models (VLMs) can reason about time-series data, thei…
Hotspot-Driven Peptide Design via Multi-Fragment Autoregressive Extension
Jiahan Li, Tong Chen, Shitong Luo +7
Peptides, short chains of amino acids, interact with target proteins, making them a unique class of protein-based therapeutics for treating human diseases. Recently, deep generativ…
Batched Contextual Reinforcement: A Task-Scaling Law for Efficient Reasoning
Bangji Yang, Hongbo Ma, Jiajun Fan +1
Large Language Models employing Chain-of-Thought reasoning achieve strong performance but suffer from excessive token consumption that inflates inference costs. Existing efficiency…
Probing the Knowledge Boundary: An Interactive Agentic Framework for Deep Knowledge Extraction
Yuheng Yang, Siqi Zhu, Tao Feng +2
Large Language Models (LLMs) can be seen as compressed knowledge bases, but it remains unclear what knowledge they truly contain and how far their knowledge boundary extends. Exist…
Incentivizing Consistent, Effective and Scalable Reasoning Capability in Audio LLMs via Reasoning Process Rewards
Jiajun Fan, Roger Ren, Jingyuan Li +6
The role of reasoning in Audio Large Language Models remains widely underexplored, as introducing a reasoning process often degrades rather than improves performance during inferen…
Teleportation of an arbitrary multipartite state via photonic Faraday rotation
Juan-Juan Chen, Jun-Hong An, Mang Feng +1
We propose a practical scheme for deterministically teleporting an arbitrary multipartite state, either product or entangled, using Faraday rotation of the photonic polarization. O…