370 citations · 1.8k across the 232 of their papers we have counts for
237 papers
Mechanist: AI as a Scientific Instrument for Discovering the Mechanisms of Intelligence
Mengru Wang, Junfeng Fang, Shuofei Qiao +17
AI models are increasingly used in scientific discovery and human decision-making. Yet how AI models work and what risks they pose remain poorly understood. As AI development becom…
EM^2Mem: Event-Centric Multimodal Memory for Large Language Models
Yijun Chen, Yaqi Zheng, Yanya Li +11
Multimodal memory offers a scalable interface for long-video question answering, but existing methods often retrieve captions, frames, transcripts, summaries, or graph facts as iso…
MobileMem: Learning from a Year of Mobile Experiences
Xinle Deng, Yida Xue, Xiangyuan Ru +16
The next generation of AI agents is increasingly moving beyond systems that answer isolated questions toward persistent personal assistants that can understand, remember, and conti…
OneDayAgent: Towards a Long-Horizon Harness for Autonomous Agents
Jingsheng Zheng, Xinyuan Fang, Jintian Zhang +3
LLM agents are increasingly applied to open-ended everyday requests that span work, study, and life. These tasks are long-horizon, cross-environment, and multimodal, forcing the ag…
When Teachers Mislead: Spurious-Signal-Aware On-Policy Distillation
Yinuo Jiang, Yongjie Ye, Zhou Tao +4
On-Policy distillation (OPD) transfers teacher capabilities by supervising student-sampled trajectories with dense token-level teacher signals. Recent selective OPD methods improve…
SciToolAgent-Evo: An Ontology-Aware Self-Evolving Agent for Open-World Scientific Tool Acquisition
Yuqi Tang, Chenyi Zhou, Libin Wang +3
Large language model (LLM) agents have been increasingly adopted in scientific research for organizing and invoking specialized computational tools. However, their reliance on pred…
OmniPhys: Knowledge-Graph-Driven Benchmarking and Collective Optimization for Physical Commonsense in Text-to-Image Generation
Yajing Xu, Yarong Lan, Jiaoyan Chen +6
While text-to-image models exhibit remarkable visual fidelity, they frequently violate fundamental physical commonsense. Existing benchmarks often rely on coarse-grained descriptio…
MolSafeEval: A Benchmark for Uncovering Safety Risks in AI-Generated Molecules
Tong Xu, Xinzhe Cao, Zhihui Zhu +2
Current molecular generation benchmarks emphasize task complexity, molecule novelty, and property alignment; they largely overlook a critical concern: the potential safety risks of…
CORTEX: High-Quality Cross-Domain Organization of Web-Scale Corpora through Ontological Corpus Graph
Chengtao Gan, Xiaoke Guo, Yushan Zhu +5
The continuous evolution of large language models drives escalating demands on data scale and quality, and as different training stages impose increasingly tailored data requiremen…
Scaling LLM Knowledge Boundaries via Distribution-Optimized Synthesis
Songze Li, Yarong Lan, Zhongpu Bo +16
Knowledge injection via synthetic data is crucial for enhancing Large Language Models (LLMs). However, current synthesis methods simply stop at preset token counts or fixed data ra…
LabVLA: Grounding Vision-Language-Action Models in Scientific Laboratories
Baochang Ren, Xinjie Liu, Xi Chen +15
Scientific laboratories increasingly rely on AI systems to reason about experiments, but the physical act of doing science remains largely outside their reach. AI can help read lit…
Symbolic and Abstractive Reasoning with Complex Visual Queries
Yichi Zhang, Jingdian Lu, Zhuo Chen +4
Understanding and reasoning over abstract visual content remains a challenge for current multi-modal large language models (MLLMs). In this paper, we explore a novel abstract data…
Unsupervised Skill Discovery for Agentic Data Analysis
Zhisong Qiu, Kangqi Song, Shengwei Tang +4
Inference-time skill augmentation provides a lightweight way to improve data-analytic agents by injecting reusable procedural knowledge without updating model parameters. However,…
Generic Interpretation Approach for Transformer Models Incorporating Heterogenous Attention Structures
Yongjin Cui, Xiaohui Fan, Huajun Chen
Transformer has significantly propelled the development of artificial intelligence, and certainly the development of agents as well. We categorize attention structures of Transform…
What's Missing in Screen-to-Action? Towards a UI-in-the-Loop Paradigm for Multimodal GUI Reasoning
Songze Li, Xiaoke Guo, Tianqi Liu +5
Existing Graphical User Interface (GUI) reasoning tasks remain challenging, particularly in UI understanding. Current methods typically rely on direct screen-based decision-making,…
Rethinking Memory as Continuously Evolving Connectivity
Jizhan Fang, Buqiang Xu, Zhixian Wang +12
Existing memory-augmented LLM agents often treat memory as a static repository with pre-defined representations and fixed retrieval pipelines, which is brittle in dynamic agentic e…
ASTRA: Adaptive Semantic Tree Reasoning Architecture for Complex Table Question Answering
Xiaoke Guo, Songze Li, Zhiqiang Liu +4
Table serialization remains a critical bottleneck for Large Language Models (LLMs) in complex table question answering, hindered by challenges such as structural neglect, represent…
ChemVA: Advancing Large Language Models on Chemical Reaction Diagrams Understanding
Mingyang Rao, Kehua Feng, Zhihui Zhu +4
While Large Language Models (LLMs) have revolutionized scientific text processing, they exhibit a significant capability gap when interpreting chemical reaction diagrams. We identi…
Transformer Interpretability from Perspective of Attention and Gradient
Yongjin Cui, Xiaohui Fan, Huajun Chen
Although researchers' attention is more focused on the performance of Transformer models, the interpretation of Transformer can never be ignored. Gradient is widely utilized in Tra…
OceanPile: A Large-Scale Multimodal Ocean Corpus for Foundation Models
Yida Xue, Ningyu Zhang, Tingwei Wu +5
The vast and underexplored ocean plays a critical role in regulating global climate and supporting marine biodiversity, yet artificial intelligence has so far delivered limited imp…
StressEval: Failure-Driven Dynamic Benchmarking for Knowledge-Intensive Reasoning in Large Language Models
Yongrui Chen, Yangyang Ma, Xiaoying Huang +4
Static benchmarks for LLMs are increasingly compromised by contamination and overfitting especially on knowledge intensive reasoning tasks While recent dynamic benchmarks can allev…
SciAtlas: A Computable Atlas of Science for Knowledge-Grounded AI Research
Shuofei Qiao, Yunxiang Wei, Busheng Zhang +16
Artificial intelligence is rapidly entering the core workflows of scientific research. Yet reliable scientific reasoning requires access to accumulated scientific knowledge with su…
How Controllable Are Large Language Models? A Unified Evaluation across Behavioral Granularities
Ziwen Xu, Kewei Xu, Haoming Xu +8
Large Language Models (LLMs) are increasingly deployed in socially sensitive domains, yet their unpredictable behaviors, ranging from misaligned intent to inconsistent personality,…
LightThinker++: From Reasoning Compression to Memory Management
Yuqi Zhu, Jintian Zhang, Zhenjie Wan +7
Large language models (LLMs) excel at complex reasoning, yet their efficiency is limited by the surging cognitive overhead of long thought traces. In this paper, we propose LightTh…