613 citations · 1.1k across the 36 of their papers we have counts for
36 papers
Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA
Mind Lab, :, Vin Bo +80
Macaron-V1 is an open agent-model family for experiential intelligence: learning from experience in real environments and continuing to learn after deployment. It is organized arou…
On the Scaling of PEFT: Towards Million Personal Models of Trillion Parameters
Mind Lab, :, Vin Bo +64
Parameter-efficient fine-tuning (PEFT) is usually treated as a cheaper alternative to full fine-tuning. We study a broader role: small trainable adapters as persistent local state…
MinT: Managed Infrastructure for Training and Serving Millions of LLMs
Mind Lab, :, Song Cao +60
We present MindLab Toolkit (MinT), a managed infrastructure system for Low-Rank Adaptation (LoRA) post-training and online serving. MinT targets a setting where many trained polici…
Self-ReSET: Learning to Self-Recover from Unsafe Reasoning Trajectories
Dongcheng Zhang, Yi Zhang, Yuxin Chen +3
Large Reasoning Models possess remarkable capabilities for self-correction in general domain; however, they frequently struggle to recover from unsafe reasoning trajectories under…
Internalizing Safety Understanding in Large Reasoning Models via Verification
Yi Zhang, Yuxin Chen, Leheng Sheng +4
While explicit Chain-of-Thought (CoT) empowers large reasoning models (LRMs), it enables the generation of riskier final answers. Current alignment paradigms primarily rely on exte…
MASKDROID: Robust Android Malware Detection with Masked Graph Representations
Jingnan Zheng, Jiaohao Liu, An Zhang +4
Android malware attacks have posed a severe threat to mobile users, necessitating a significant demand for the automated detection system. Among the various tools employed in malwa…
Customizing Language Models with Instance-wise LoRA for Sequential Recommendation
Xiaoyu Kong, Jiancan Wu, An Zhang +4
Sequential recommendation systems predict the next interaction item based on users' past interactions, aligning recommendations with individual preferences. Leveraging the strength…
Disentangling Masked Autoencoders for Unsupervised Domain Generalization
An Zhang, Han Wang, Xiang Wang +1
Domain Generalization (DG), designed to enhance out-of-distribution (OOD) generalization, is all about learning invariance against domain shifts utilizing sufficient supervision si…
Language Representations Can be What Recommenders Need: Findings and Potentials
Leheng Sheng, An Zhang, Yi Zhang +3
Recent studies empirically indicate that language models (LMs) encode rich world knowledge beyond mere semantics, attracting significant attention across various fields. However, i…
On Softmax Direct Preference Optimization for Recommendation
Yuxin Chen, Junfei Tan, An Zhang +5
Recommender systems aim to predict personalized rankings based on user preference data. With the rise of Language Models (LMs), LM-based recommenders have been widely explored due…
Hello Again! LLM-powered Personalized Agent for Long-term Dialogue
Hao Li, Chenghao Yang, An Zhang +3
Open-domain dialogue systems have seen remarkable advancements with the development of large language models (LLMs). Nonetheless, most existing dialogue systems predominantly focus…
ReactXT: Understanding Molecular "Reaction-ship" via Reaction-Contextualized Molecule-Text Pretraining
Zhiyuan Liu, Yaorui Shi, An Zhang +5
Molecule-text modeling, which aims to facilitate molecule-relevant tasks with a textual interface and textual knowledge, is an emerging research direction. Beyond single molecules,…
ProtT3: Protein-to-Text Generation for Text-based Protein Understanding
Zhiyuan Liu, An Zhang, Hao Fei +4
Language Models (LMs) excel in understanding textual descriptions of proteins, as evident in biomedical question-answering tasks. However, their capability falters with raw protein…
ALI-Agent: Assessing LLMs' Alignment with Human Values via Agent-based Evaluation
Jingnan Zheng, Han Wang, An Zhang +3
Large Language Models (LLMs) can elicit unintended and even harmful content when misaligned with human values, posing severe risks to users and society. To mitigate these risks, cu…
General Debiasing for Graph-based Collaborative Filtering via Adversarial Graph Dropout
An Zhang, Wenchang Ma, Pengbo Wei +2
Graph neural networks (GNNs) have shown impressive performance in recommender systems, particularly in collaborative filtering (CF). The key lies in aggregating neighborhood inform…
Towards Goal-oriented Intelligent Tutoring Systems in Online Education
Yang Deng, Zifeng Ren, An Zhang +1
Interactive Intelligent Tutoring Systems (ITSs) enhance traditional ITSs by promoting effective learning through interactions and problem resolution in online education. Yet, proac…
Large Language Model Can Interpret Latent Space of Sequential Recommender
Zhengyi Yang, Jiancan Wu, Yanchen Luo +5
Sequential recommendation is to predict the next item of interest for a user, based on her/his interaction history with previous items. In conventional sequential recommenders, a c…
Empowering Collaborative Filtering with Principled Adversarial Contrastive Loss
An Zhang, Leheng Sheng, Zhibo Cai +2
Contrastive Learning (CL) has achieved impressive performance in self-supervised learning tasks, showing superior generalization ability. Inspired by the success, adopting CL into…
ReLM: Leveraging Language Models for Enhanced Chemical Reaction Prediction
Yaorui Shi, An Zhang, Enzhi Zhang +2
Predicting chemical reactions, a fundamental challenge in chemistry, involves forecasting the resulting products from a given reaction process. Conventional techniques, notably tho…
Robust Collaborative Filtering to Popularity Distribution Shift
An Zhang, Wenchang Ma, Jingnan Zheng +2
In leading collaborative filtering (CF) models, representations of users and items are prone to learn popularity bias in the training data as shortcuts. The popularity shortcut tri…
Rethinking Tokenizer and Decoder in Masked Graph Modeling for Molecules
Zhiyuan Liu, Yaorui Shi, An Zhang +4
Masked graph modeling excels in the self-supervised representation learning of molecular graphs. Scrutinizing previous studies, we can reveal a common scheme consisting of three ke…
On Generative Agents in Recommendation
An Zhang, Yuxin Chen, Leheng Sheng +2
Recommender systems are the cornerstone of today's information dissemination, yet a disconnect between offline metrics and online performance greatly hinders their development. Add…
Online Distillation-enhanced Multi-modal Transformer for Sequential Recommendation
Wei Ji, Xiangyan Liu, An Zhang +3
Multi-modal recommendation systems, which integrate diverse types of information, have gained widespread attention in recent years. However, compared to traditional collaborative f…
Redundancy-aware Transformer for Video Question Answering
Yicong Li, Xun Yang, An Zhang +3
This paper identifies two kinds of redundancy in the current VideoQA paradigm. Specifically, the current video encoders tend to holistically embed all video clues at different gran…