27 citations · 71 across the 26 of their papers we have counts for
26 papers
ROAM: Robust Organization of Atomic Memories for Agents through Semantic Relations
Jianjie Zheng, Peng Lai, Sijie Cheng +3
Long-term language-model agents rely on external memory across interactions. Atomic memories are particularly useful: their fine-grained semantic boundaries enable precise retrieva…
CADER: Confidence-Aware Dynamic Evidence Reasoning for Long-Video Understanding
Jinlong Yang, Wenhao Zhang, Kuanwei Lin +1
Long-video understanding increasingly relies on large vision-language models and tool-augmented reasoning, but most systems apply the same inference procedure to every example rega…
AnchorMem: Anchored Facts with Associative Contexts for Building Memory in Large Language Models
Zhanyu Shen, Sijie Cheng, Zhicheng Guo +3
While large language models have achieved remarkable performance in complex tasks, they still need a memory system to utilize historical experience in long-term interactions. Exist…
Evaluating Memory Capability in Continuous Lifelog Scenario
Jianjie Zheng, Zhichen Liu, Zhanyu Shen +6
Nowadays, wearable devices can continuously lifelog ambient conversations, creating substantial opportunities for memory systems. However, existing benchmarks primarily focus on on…
VideoMem: Enhancing Ultra-Long Video Understanding via Adaptive Memory Management
Hongbo Jin, Qingyuan Wang, Wenhao Zhang +2
Ultra long video understanding remains an open challenge, as existing vision language models (VLMs) falter on such content due to limited context length and inefficient long term m…
Building Egocentric Procedural AI Assistant: Methods, Benchmarks, and Challenges
Junlong Li, Huaiyuan Xu, Sijie Cheng +4
Driven by recent advances in vision-language models (VLMs) and egocentric perception research, the emerging topic of an egocentric procedural AI assistant (EgoProceAssist) is intro…
Beyond the Surface: Enhancing LLM-as-a-Judge Alignment with Human via Internal Representations
Peng Lai, Jianjie Zheng, Sijie Cheng +4
The growing scale of evaluation tasks has led to the widespread adoption of automated evaluation using LLMs, a paradigm known as "LLM-as-a-judge". However, improving its alignment…
StableToolBench-MirrorAPI: Modeling Tool Environments as Mirrors of 7,000+ Real-World APIs
Zhicheng Guo, Sijie Cheng, Yuchen Niu +4
The rapid advancement of large language models (LLMs) has spurred significant interest in tool learning, where LLMs are augmented with external tools to tackle complex tasks. Howev…
VidEgoThink: Assessing Egocentric Video Understanding Capabilities for Embodied AI
Sijie Cheng, Kechen Fang, Yangyang Yu +6
Recent advancements in Multi-modal Large Language Models (MLLMs) have opened new avenues for applications in Embodied AI. Building on previous work, EgoThink, we introduce VidEgoTh…
ConvLLaVA: Hierarchical Backbones as Visual Encoder for Large Multimodal Models
Chunjiang Ge, Sijie Cheng, Ziming Wang +6
High-resolution Large Multimodal Models (LMMs) encounter the challenges of excessive visual tokens and quadratic visual complexity. Current high-resolution LMMs address the quadrat…
StableToolBench: Towards Stable Large-Scale Benchmarking on Tool Learning of Large Language Models
Zhicheng Guo, Sijie Cheng, Hao Wang +6
Large Language Models (LLMs) have witnessed remarkable advancements in recent years, prompting the exploration of tool learning, which integrates LLMs with external tools to addres…
DEEM: Dynamic Experienced Expert Modeling for Stance Detection
Xiaolong Wang, Yile Wang, Sijie Cheng +2
Recent work has made a preliminary attempt to use large language models (LLMs) to solve the stance detection task, showing promising results. However, considering that stance detec…
Speak It Out: Solving Symbol-Related Problems with Symbol-to-Language Conversion for Language Models
Yile Wang, Sijie Cheng, Zixin Sun +2
Symbols (or more broadly, non-natural language textual representations) such as numerical sequences, molecular formulas, and table delimiters widely exist, playing important roles…
EgoThink: Evaluating First-Person Perspective Thinking Capability of Vision-Language Models
Sijie Cheng, Zhicheng Guo, Jingwen Wu +4
Vision-language models (VLMs) have recently shown promising results in traditional downstream tasks. Evaluation studies have emerged to assess their abilities, with the majority fo…
OpenChat: Advancing Open-source Language Models with Mixed-Quality Data
Guan Wang, Sijie Cheng, Xianyuan Zhan +3
Nowadays, open-source large language models like LLaMA have emerged. Recent developments have incorporated supervised fine-tuning (SFT) and reinforcement learning fine-tuning (RLFT…
Offline Reinforcement Learning with Imbalanced Datasets
Li Jiang, Sijie Cheng, Jielin Qiu +3
The prevalent use of benchmarks in current offline reinforcement learning (RL) research has led to a neglect of the imbalance of real-world dataset distributions in the development…
Prompt-Guided Retrieval Augmentation for Non-Knowledge-Intensive Tasks
Zhicheng Guo, Sijie Cheng, Yile Wang +2
Retrieval-augmented methods have received increasing attention to support downstream tasks by leveraging useful information from external resources. Recent studies mainly focus on…
Evolving Connectivity for Recurrent Spiking Neural Networks
Guan Wang, Yuhao Sun, Sijie Cheng +1
Recurrent spiking neural networks (RSNNs) hold great potential for advancing artificial general intelligence, as they draw inspiration from the biological nervous system and show p…
Modeling Adversarial Attack on Pre-trained Language Models as Sequential Decision Making
Xuanjie Fang, Sijie Cheng, Yang Liu +1
Pre-trained language models (PLMs) have been widely used to underpin various downstream tasks. However, the adversarial attack task has found that PLMs are vulnerable to small pert…
Say What You Mean! Large Language Models Speak Too Positively about Negative Commonsense Knowledge
Jiangjie Chen, Wei Shi, Ziquan Fu +3
Large language models (LLMs) have been widely studied for their ability to store and utilize positive knowledge. However, negative knowledge, such as "lions don't live in the ocean…
Unsupervised Explanation Generation via Correct Instantiations
Sijie Cheng, Zhiyong Wu, Jiangjie Chen +3
While large pre-trained language models (PLM) have shown their great skills at solving discriminative tasks, a significant gap remains when compared with humans for explanation-rel…
Learning What You Need from What You Did: Product Taxonomy Expansion with User Behaviors Supervision
Sijie Cheng, Zhouhong Gu, Bang Liu +3
Taxonomies have been widely used in various domains to underpin numerous applications. Specially, product taxonomies serve an essential role in the e-commerce domain for the recomm…
Can Pre-trained Language Models Interpret Similes as Smart as Human?
Qianyu He, Sijie Cheng, Zhixu Li +2
Simile interpretation is a crucial task in natural language processing. Nowadays, pre-trained language models (PLMs) have achieved state-of-the-art performance on many tasks. Howev…
Unsupervised Editing for Counterfactual Stories
Jiangjie Chen, Chun Gan, Sijie Cheng +3
Creating what-if stories requires reasoning about prior statements and possible outcomes of the changed conditions. One can easily generate coherent endings under new conditions, b…