2 citations · 3 across the 24 of their papers we have counts for
25 papers
Function-Aware Fill-in-the-Middle as Mid-Training for Coding Agent Foundation Models
Yubo Wang, Jiarong Liang, Yuxuan Zhang +5
Coding agents must integrate external tool returns into ongoing reasoning - a capability that standard left-to-right pretraining on code exposes only in its forward direction. We o…
Dr-DCI: Scaling Direct Corpus Interaction via Dynamic Workspace Expansion
Yi Lu, Zhuofeng Li, Ping Nie +7
Agentic search over large corpora relies on retriever-mediated interfaces (e.g., BM25 or ColBERT) for scalable candidate discovery. While effective at ranking relevant documents, t…
WorldReasonBench: Human-Aligned Stress Testing of Video Generators as Future World-State Predictors
Keming Wu, Yijing Cui, Wenhan Xue +11
Commercial video generation systems such as Seedance2.0 and Veo3.1 have rapidly improved, strengthening the view that video generators may be evolving into "world simulators." Yet…
RewardHarness: Self-Evolving Agentic Post-Training
Yuxuan Zhang, Penghui Du, Bo Li +11
Aligning generative models with human preferences remains a central challenge. While RLHF is widely adopted, it relies on large-scale preference data. This limitation is particular…
Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction
Zhuofeng Li, Haoxiang Zhang, Cong Wei +16
Modern retrieval systems, whether lexical or semantic, expose a corpus through a fixed similarity interface that compresses access into a single top-k retrieval step before reasoni…
ClawBench: Can AI Agents Complete Everyday Online Tasks?
Yuxuan Zhang, Yubo Wang, Yipeng Zhu +25
AI agents may be able to assist with emails and documents, but can they reliably complete everyday online workflows on real websites? Everyday online tasks offer a realistic yet un…
ImagenWorld: Stress-Testing Image Generation Models with Explainable Human Evaluation on Open-ended Real-World Tasks
Samin Mahdizadeh Sani, Max Ku, Nima Jamali +23
Advances in diffusion, autoregressive, and hybrid models have enabled high-quality image synthesis for tasks such as text-to-image, editing, and reference-guided composition. Yet,…
SWE-Next: Scalable Real-World Software Engineering Tasks for Agents
Jiarong Liang, Zhiheng Lyu, Zijie Liu +4
Executable software engineering data is valuable for training SWE agents, but scaling it remains difficult for two reasons: only a small fraction of real repository changes yield v…
EvolveCoder: Evolving Test Cases via Adversarial Verification for Code Reinforcement Learning
Chi Ruan, Dongfu Jiang, Huaye Zeng +2
Reinforcement learning with verifiable rewards (RLVR) is a promising approach for improving code generation in large language models, but its effectiveness is limited by weak and s…
OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis
Zhuofeng Li, Dongfu Jiang, Xueguang Ma +7
Training deep research agents requires long-horizon trajectories that interleave search, evidence aggregation, and multi-step reasoning. However, existing data collection pipelines…
VisPhyWorld: Probing Physical Reasoning via Code-Driven Video Reconstruction
Jiarong Liang, Max Ku, Ka-Hei Hui +2
Evaluating whether Multimodal Large Language Models (MLLMs) genuinely reason about physical dynamics remains challenging. Most existing benchmarks rely on recognition-style protoco…
BrowserAgent: Building Web Agents with Human-Inspired Web Browsing Actions
Tao Yu, Zhengbo Zhang, Zhiheng Lyu +8
Efficiently solving real-world problems with LLMs increasingly hinges on their ability to interact with dynamic web environments and autonomously acquire external information. Whil…
VisCoder2: Building Multi-Language Visualization Coding Agents
Yuansheng Ni, Songcheng Cai, Xiangchao Chen +8
Large language models (LLMs) have recently enabled coding agents capable of generating, executing, and revising visualization code. However, existing models often fail in practical…
VideoScore2: Think before You Score in Generative Video Evaluation
Xuan He, Dongfu Jiang, Ping Nie +21
Recent advances in text-to-video generation have produced increasingly realistic and diverse content, yet evaluating such videos remains a fundamental challenge due to their multi-…
EditReward: A Human-Aligned Reward Model for Instruction-Guided Image Editing
Keming Wu, Sicong Jiang, Max Ku +3
Recently, we have witnessed great progress in image editing with natural language instructions. Several closed-source models like GPT-Image-1, Seedream, and Google-Nano-Banana have…
Critique-Coder: Enhancing Coder Models by Critique Reinforcement Learning
Chi Ruan, Dongfu Jiang, Yubo Wang +1
Reinforcement Learning (RL) has emerged as a popular training paradigm, particularly when paired with reasoning models. While effective, it primarily focuses on generating response…
Unleashing the Reasoning Potential of Pre-trained LLMs by Critique Fine-Tuning on One Problem
Yubo Wang, Ping Nie, Kai Zou +2
We have witnessed that strong LLMs like Qwen-Math, MiMo, and Phi-4 possess immense reasoning potential inherited from the pre-training stage. With reinforcement learning (RL), thes…
VisCoder: Fine-Tuning LLMs for Executable Python Visualization Code Generation
Yuansheng Ni, Ping Nie, Kai Zou +2
Large language models (LLMs) often struggle with visualization tasks like plotting diagrams, charts, where success depends on both code correctness and visual semantics. Existing i…
QuickVideo: Real-Time Long Video Understanding with System Algorithm Co-Design
Benjamin Schneider, Dongfu Jiang, Chao Du +2
Long-video understanding has emerged as a crucial capability in real-world applications such as video surveillance, meeting summarization, educational lecture analysis, and sports…
StructEval: Benchmarking LLMs' Capabilities to Generate Structural Outputs
Jialin Yang, Dongfu Jiang, Lipeng He +17
As Large Language Models (LLMs) become integral to software development workflows, their ability to generate structured outputs has become critically important. We introduce Struct…
Breaking the Batch Barrier (B3) of Contrastive Learning via Smart Batch Mining
Raghuveer Thirukovalluru, Rui Meng, Ye Liu +7
Contrastive learning (CL) is a prevalent technique for training embedding models, which pulls semantically similar examples (positives) closer in the representation space while pus…
ScholarCopilot: Training Large Language Models for Academic Writing with Accurate Citations
Yubo Wang, Xueguang Ma, Ping Nie +7
Academic writing requires both coherent text generation and precise citation of relevant literature. Although recent Retrieval-Augmented Generation (RAG) systems have significantly…
VisualWebInstruct: Scaling up Multimodal Instruction Data through Web Search
Yiming Jia, Jiachen Li, Xiang Yue +4
Vision-Language Models have made significant progress on many perception-focused tasks. However, their progress on reasoning-focused tasks remains limited due to the lack of high-q…
ABC: Achieving Better Control of Multimodal Embeddings using VLMs
Benjamin Schneider, Florian Kerschbaum, Wenhu Chen
Visual embedding models excel at zero-shot tasks like visual retrieval and classification. However, these models cannot be used for tasks that contain ambiguity or require user ins…