Publications (39)
LettinGo: Explore User Profile Generation for Recommendation System
Lu Wang, Di Zhang, Fangkai Yang +9
User profiling is pivotal for recommendation systems, as it transforms raw user interaction data into concise and structured representations that drive personalized recommendations…
A Deep Model for Partial Multi-Label Image Classification with Curriculum Based Disambiguation
Feng Sun, Ming-Kun Xie, Sheng-Jun Huang
In this paper, we study the partial multi-label (PML) image classification problem, where each image is annotated with a candidate label set consists of multiple relevant labels an…
MTL-LoRA: Low-Rank Adaptation for Multi-Task Learning
Yaming Yang, Dilxat Muhtar, Yelong Shen +9
Parameter-efficient fine-tuning (PEFT) has been widely employed for domain adaptation, with LoRA being one of the most prominent methods due to its simplicity and effectiveness. Ho…
E5-V: Universal Embeddings with Multimodal Large Language Models
Ting Jiang, Minghui Song, Zihan Zhang +6
Multimodal large language models (MLLMs) have shown promising advancements in general visual and language understanding. However, the representation of multimodal information using…
Effects of biaxial strain and local constant potential on electronic structure of monolayer SnSe
Feng Sun, Ting Luo, Lin Li +3
We use the modified Becke-Johnson exchange potential (mBJ) with the spin-orbit coupling effect (SOC) to study effects of biaxial strain and local constant potential on electronic s…
Crystal structures and electronic and magnetic properties of Janus bilayer Cl3Cr2I3
Suqi Liu, Feng Sun, Aijun Hong
Two-dimensional (2D) magnetic material CrI3 has aroused extensive attention, because it could provide a new platform for investigating the relations between crystal structures and…
Token-level Proximal Policy Optimization for Query Generation
Yichen Ouyang, Lu Wang, Fangkai Yang +13
Query generation is a critical task for web search engines (e.g. Google, Bing) and recommendation systems. Recently, state-of-the-art query generation methods leverage Large Langua…
Re-understanding of the deformation potential constant in the single crystal silicon
Feng Sun, Aijun Hong
The mobility formula based on deformation potential (DP) theory is of great importance in semiconductor physics. However, the related calculations for the DP constant are controver…
Unleash LLMs Potential for Recommendation by Coordinating Twin-Tower Dynamic Semantic Token Generator
Jun Yin, Zhengxin Zeng, Mingzheng Li +11
Owing to the unprecedented capability in semantic understanding and logical reasoning, the pre-trained large language models (LLMs) have shown fantastic potential in developing the…
MoRA: High-Rank Updating for Parameter-Efficient Fine-Tuning
Ting Jiang, Shaohan Huang, Shengyue Luo +8
Low-rank adaptation is a popular parameter-efficient fine-tuning method for large language models. In this paper, we analyze the impact of low-rank updating, as implemented in LoRA…
Calibrating LLM-Based Evaluator
Yuxuan Liu, Tianchi Yang, Shaohan Huang +6
Recent advancements in large language models (LLMs) on language modeling and emergent capabilities make them a promising reference-free evaluator of natural language generation qua…
Beyond Static Dialogues: Benchmarking Realistic, Heterogeneous, and Evolving Long-Term Memory
Han Zhang, Zihao Tang, Xin Yu +8
In existing memory benchmarks for Large Language Models (LLMs), the evaluated dialogue sessions often lack long-term semantic consistency, and the underlying personas tend to be fl…
Influence of different exchange-correlation potentials on twisted structures of bilayer XS2 (X= Mo, Cr)
Feng Sun, Ting Luo, Lin Li +3
In this work, we employ the LDA, GGA and GGA with four vdW corrections to study crystal and electronic structures of bilayer transition metal dichalcogenides (TMDs) with different…
Continuous Collision Detection for Composite Quadric Models
Yi-King Choi, Wenping Wang, Bernard Mourrain +3
A composite quadric model (CQM) is an object modeled by piecewise linear or quadric patches. We study the continuous detection problem of a special type of CQM objects which are co…
AdNanny: One Reasoning LLM for All Offline Ads Recommendation Tasks
Nan Hu, Han Li, Jimeng Sun +16
Large Language Models (LLMs) have shown strong capabilities in Natural Language Understanding and Generation, but deploying them directly in online advertising systems is often imp…
ResLoRA: Identity Residual Mapping in Low-Rank Adaption
Shuhua Shi, Shaohan Huang, Minghui Song +7
As one of the most popular parameter-efficient fine-tuning (PEFT) methods, low-rank adaptation (LoRA) is commonly applied to fine-tune large language models (LLMs). However, updati…
Democratizing Reasoning Ability: Tailored Learning from Large Language Model
Zhaoyang Wang, Shaohan Huang, Yuxuan Liu +8
Large language models (LLMs) exhibit impressive emergent abilities in natural language processing, but their democratization is hindered due to huge computation requirements and cl…
Context-DPO: Aligning Language Models for Context-Faithfulness
Baolong Bi, Shaohan Huang, Yiwei Wang +11
Reliable responses from large language models (LLMs) require adherence to user instructions and retrieved information. While alignment techniques help LLMs align with human intenti…
StreamAdapter: Efficient Test Time Adaptation from Contextual Streams
Dilxat Muhtar, Yelong Shen, Yaming Yang +11
In-context learning (ICL) allows large language models (LLMs) to adapt to new tasks directly from the given demonstrations without requiring gradient updates. While recent advances…
RRLFSOR: An Efficient Self-Supervised Learning Strategy of Graph Convolutional Networks
Feng Sun, Ajith Kumar, Guanci Yang +4
Graph Convolutional Networks (GCNs) are widely used in many applications yet still need large amounts of labelled data for training. Besides, the adjacency matrix of GCNs is stable…
Single Atom Catalysts with Halogen Ligands: Elevating the HER Performance of Pd-anchored MoS2 monolayer
Feng Sun, Xuqiang Zhang, Jiangtao Chen +2
Single-atom catalysts (SACs) have attracted ever-growing interest due to their high atom-utilization efficiency and potential for cost-effective of hydrogen production. However, en…
Improving Domain Adaptation through Extended-Text Reading Comprehension
Ting Jiang, Shaohan Huang, Shengyue Luo +8
To enhance the domain-specific capabilities of large language models, continued pre-training on a domain-specific corpus is a prevalent method. Recent work demonstrates that adapti…
RePrompt: Reasoning-Augmented Reprompting for Text-to-Image Generation via Reinforcement Learning
Mingrui Wu, Lu Wang, Pu Zhao +14
Despite recent progress in text-to-image (T2I) generation, existing models often struggle to faithfully capture user intentions from short and under-specified prompts. While prior…
Auto Search Indexer for End-to-End Document Retrieval
Tianchi Yang, Minghui Song, Zihan Zhang +4
Generative retrieval, which is a new advanced paradigm for document retrieval, has recently attracted research interests, since it encodes all documents into the model and directly…
LGM: Enhancing Large Language Models with Conceptual Meta-Relations and Iterative Retrieval
Wenchang Lei, Ping Zou, Yue Wang +2
Large language models (LLMs) exhibit strong semantic understanding, yet struggle when user instructions involve ambiguous or conceptually misaligned terms. We propose the Language…
Mnemis: Dual-Route Retrieval on Hierarchical Graphs for Long-Term LLM Memory
Zihao Tang, Xin Yu, Ziyu Xiao +9
AI Memory, specifically how models organizes and retrieves historical messages, becomes increasingly valuable to Large Language Models (LLMs), yet existing methods (RAG and Graph-R…
ASI++: Towards Distributionally Balanced End-to-End Generative Retrieval
Yuxuan Liu, Tianchi Yang, Zihan Zhang +5
Generative retrieval, a promising new paradigm in information retrieval, employs a seq2seq model to encode document features into parameters and decode relevant document identifier…
Computing a Compact Spline Representation of the Medial Axis Transform of a 2D Shape
Yanshu Zhu, Feng Sun, Yi-King Choi +2
We present a full pipeline for computing the medial axis transform of an arbitrary 2D shape. The instability of the medial axis transform is overcome by a pruning algorithm guided…
GeAR: Generation Augmented Retrieval
Haoyu Liu, Shaohan Huang, Jianfeng Liu +6
Document retrieval techniques are essential for developing large-scale information systems. The common approach involves using a bi-encoder to compute the semantic similarity betwe…
MMINR: Multi-frame-to-Multi-frame Inference with Noise Resistance for Precipitation Nowcasting with Radar
Feng Sun, Cong Bai
Precipitation nowcasting based on radar echo maps is essential in meteorological research. Recently, Convolutional RNNs based methods dominate this field, but they cannot be solved…
Group-Graph Policy Optimization for Long-Horizon Agentic Reinforcement Learning
Yunan Wang, Minghui Song, Zihan Zhang +6
Group-based Reinforcement Learning (RL) has significantly enhanced Large Language Models (LLMs) in agentic scenarios. To achieve finer-grained policy updates, recent agentic RL fra…
Hybrid Modeling Application in Control Valve
Yuan Chi, He Xu, Feng Sun +1
In view of the serious nonlinearity, time-varying and parameter uncertainty in the physical model of regulating valve, a prediction model of flow rate and pressure of regulating va…
MAIN: Mutual Alignment Is Necessary for instruction tuning
Fanyi Yang, Jianfeng Liu, Xin Zhang +7
Instruction tuning has empowered large language models (LLMs) to achieve remarkable performance, yet its success heavily depends on the availability of large-scale, high-quality in…
DUET: Joint Exploration of User Item Profiles in Recommendation System
Yue Chen, Yifei Sun, Lu Wang +17
Traditional recommendation systems represent users and items as dense vectors and learn to align them in a shared latent space for relevance estimation. Recent LLM-based recommende…
Medial Meshes for Volume Approximation
Feng Sun, Yi-King Choi, Yizhou Yu +1
Volume approximation is an important problem found in many applications of computer graphics, vision, and image processing. The problem is about computing an accurate and compact a…
Network experimentation at scale
Brian Karrer, Liang Shi, Monica Bhole +5
We describe our framework, deployed at Facebook, that accounts for interference between experimental units through cluster-randomized experiments. We document this system, includin…
Text Diffusion with Reinforced Conditioning
Yuxuan Liu, Tianchi Yang, Shaohan Huang +6
Diffusion models have demonstrated exceptional capability in generating high-quality images, videos, and audio. Due to their adaptiveness in iterative refinement, they provide a st…
Prediction for structure stability and ultrahigh hydrogen evolution performance of monolayer 2H-CrS2
Feng Sun, Aijun Hong, Wenda Zhou +2
By a combination of the first-principles calculations and climbing image nudged elastic band method (ciNEB) we investigate structure stabilities and hydrogen evolution reaction (HE…
HD-Eval: Aligning Large Language Model Evaluators Through Hierarchical Criteria Decomposition
Yuxuan Liu, Tianchi Yang, Shaohan Huang +6
Large language models (LLMs) have emerged as a promising alternative to expensive human evaluations. However, the alignment and coverage of LLM-based evaluations are often limited…