2 citations · 5 across the 37 of their papers we have counts for
42 papers
World Editing: Intervening on Executable Worlds at Increasing Depth
Max Ku, Nok-Kan Law, Yu-Chien Tang +15
Interactive world models are increasingly capable of generating environments and acting within them, yet deliberately editing an existing executable world remains underexplored. We…
VIEScore2: Unified Image Evaluation with Spatially Grounded Explanations
Xianda Du, Max Ku, Weiming Ren +5
Existing synthetic image evaluators typically provide only a scalar quality score and do not identify the image regions that support it. We introduce VIEScore2, a unified evaluator…
OPIS: An Input-Grounded Benchmark for Multi-Object Memory in Video World Models
Hao Wang, Tao Yu, Liuzhou Zhang +13
Video world models must preserve the visual state of the world over time, but existing evaluation protocols often rely on generated histories, video reference, or selected revisit…
Sequential Beats Joint: On the Interplay between On-Policy Distillation and RLVR
Boyan Li, Bingsen Chen, Chenghao Yang +3
Reinforcement learning with verifiable rewards (RLVR) and on-policy distillation (OPD) have emerged as two dominant methods for post-training reasoning LLMs. Prior work uses OPD's…
VGI-Bench: Probing Visual Intelligence in Video Generation Models
Xuan He, Cong Wei, Yuhao Cheng +20
Recent studies suggest that video generation models can exhibit certain forms of zero-shot visual reasoning through generated frames. Yet reliable evaluation remains challenging: b…
Search Beyond What Can Be Taught: Evolving the Knowledge Boundary in Agentic Visual Generation
Haozhe Wang, Weijia Feng, Jinpeng Yu +8
Visual generators excel at rendering, but they confidently fabricate what they do not know. User requests are unbounded, evolving, and deeply long-tailed: new characters, trending…
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…
SETA: Scaling Environments for Terminal Agents
Qijia Shen, Zhiqi Huang, Vamsidhar Kamanuru +19
Large language models (LLMs) are rapidly shifting toward agents that solve tasks through diverse interfaces, including web and graphical user interfaces (GUIs). Among these, the te…
miniReranker: Efficient Multimodal Reranking through Visual Cache Reuse and Interaction Sparsity
Yingqi Fan, Xuan Lu, Anhao Zhao +6
Multimodal large language models (MLLMs) have recently shown strong potential as point-wise rerankers by directly modeling query--document relevance through next-token prediction.…
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…
What Happens Before Decoding? Prefill Determines GUI Grounding in VLMs
Jiaping Lin, Fei Shen, Junzhe Li +4
Existing training-free approaches for GUI grounding often rely on multiple inference runs, such as iterative cropping or candidate aggregation, to identify target elements. Despite…
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…
FlexSQL: Flexible Exploration and Execution Make Better Text-to-SQL Agents
Quang Hieu Pham, Yang He, Ping Nie +5
Text-to-SQL over large analytical databases requires navigating complex schemas, resolving ambiguous queries, and grounding decisions in actual data. Most current systems follow a…
Watch Before You Answer: Learning from Visually Grounded Post-Training
Yuxuan Zhang, EunJeong Hwang, Huaisong Zhang +8
It is critical for vision-language models (VLMs) to comprehensively understand visual, temporal, and textual cues. However, despite rapid progress in multimodal modeling, video und…
MMEB-V3: Measuring the Performance Gaps of Omni-Modality Embedding Models
Haohang Huang, Xuan Lu, Mingyi Su +9
Multimodal embedding models aim to map heterogeneous inputs, such as text, images, videos, and audio, into a shared semantic space. However, existing methods and benchmarks remain…
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…
SWE-QA-Pro: A Representative Benchmark and Scalable Training Recipe for Repository-Level Code Understanding
Songcheng Cai, Zhiheng Lyu, Yuansheng Ni +13
Agentic repository-level code understanding is essential for automating complex software engineering tasks, yet the field lacks reliable benchmarks. Existing evaluations often over…
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…
Beyond Closed-Pool Video Retrieval: A Benchmark and Agent Framework for Real-World Video Search and Moment Localization
Tao Yu, Yujia Yang, Haopeng Jin +17
Traditional video retrieval benchmarks focus on matching precise descriptions to closed video pools, failing to reflect real-world searches characterized by fuzzy, multi-dimensiona…
Context Forcing: Consistent Autoregressive Video Generation with Long Context
Shuo Chen, Cong Wei, Sun Sun +5
Recent approaches to real-time long video generation typically employ streaming tuning strategies, attempting to train a long-context student using a short-context (memoryless) tea…