11 papers
4DMemory: Benchmarking Long-Horizon Spatiotemporal Memory with Harness-Augmented Agents
Yanhao Jia, Yi Zhu, Yiran Zhong +7
Humans efficiently process multimodal streams spanning hours to years, building persistent, fine-grained spatiotemporal memories that support reasoning about and predicting long-ho…
ScienceClaw: Benchmarking Continual Self-Evolution of AI-for-Science Agents Across the Natural and Social Sciences
Mingda Zhang, Wenjin Liu, Tiesunlong Shen +6
Large language model agents are accelerating scientific automation, yet verified executions rarely become persistent program-level improvements, and existing evaluations do not exa…
Reinforcement Learning with Comparative Evidence for Social Intelligence
Keane Ong, Yuriel Ryan, Sabri Boughorbel +9
Developing socially intelligent AI remains heavily dependent on human-annotated data, limiting the scale and breadth of social understanding models can acquire. Methods that derive…
MMOE: Modernizing Diffusion Transformers with Efficient Expert Design
Yanhao Jia, Jiepeng Wang, Haibin Huang +3
Modern large language models scale successfully by pairing capacity growth with efficiency, keeping per-token and deployment costs under control as capacity grows. AIGC Foundation…
From Static Risk to Dynamic Trajectories: Toward World-Model-Inspired Clinical Prediction
Pujun Feng, Xiaoyu Guo, Seyed Ehsan Saffari +10
Clinical decision-making is a feedback system where risk estimates influence treatment, which in turn changes disease trajectories, and both shape clinicians' measurement practices…
SkillFlow: Flow-Driven Recursive Skill Evolution for Agentic Orchestration
Mingda Zhang, Tiesunlong Shen, Haoran Luo +4
In recent years, a variety of powerful LLM-based agentic systems have been applied to automate complex tasks through task orchestration. However, existing orchestration methods sti…
EduStory: A Unified Framework for Pedagogically-Consistent Multi-Shot STEM Instructional Video Generation
Xinyi Wu, Jayant Teotia, Shuai Zhao +1
Long-horizon video generation has advanced in visual quality, yet existing methods still struggle to maintain knowledge consistency and coherent pedagogical narratives across multi…
Affective Flow Language Model for Emotional Support Conversation
Chenghui Zou, Ning Wang, Tiesunlong Shen +5
Large language models (LLMs) have advanced emotional support conversation, but existing alignment methods rely mainly on sparse preferences at the response level or outcomes at the…
FlowSteer: Towards Agents Designing Agentic Workflows via Reinforced Progressive Canvas Editing
Mingda Zhang, Wenjin Liu, Tiesunlong Shen +5
In recent years, agentic workflows have been widely applied to solve complex human tasks. However, existing workflow construction still faces key challenges, including human-depend…
LLMdoctor: Token-Level Flow-Guided Preference Optimization for Efficient Test-Time Alignment of Large Language Models
Tiesunlong Shen, Rui Mao, Jin Wang +4
Aligning Large Language Models (LLMs) with human preferences is critical, yet traditional fine-tuning methods are computationally expensive and inflexible. While test-time alignmen…
Prompt-R1: Collaborative Automatic Prompting Framework via End-to-end Reinforcement Learning
Wenjin Liu, Haoran Luo, Xueyuan Lin +5
Recently, advanced large language models (LLMs) have emerged at an increasingly rapid pace. However, when faced with complex problems, most users are often unable to provide accura…