Xiangxiang Chu

SkillClaw: Let Skills Evolve Collectively with Agentic Evolver

arXiv 2026

SaaSBench: Exploring the Boundaries of Coding Agents in Long-Horizon Enterprise SaaS Engineering

arXiv 2026

Extending One-Step Image Generation from Class Labels to Text via Discriminative Text Representation

arXiv 2026

Learning Agentic Policy from Action Guidance

arXiv 2026

Geometry-Guided Reinforcement Learning for Multi-view Consistent 3D Scene Editing

arXiv 2026

TransitLM: A Large-Scale Dataset and Benchmark for Map-Free Transit Route Generation

arXiv 2026

Urban Socio-Semantic Segmentation with Vision-Language Reasoning

arXiv 2026

Harder Is Better: Boosting Mathematical Reasoning via Difficulty-Aware GRPO and Multi-Aspect Question Reformulation

arXiv 2026

Elucidating the SNR-t Bias of Diffusion Probabilistic Models

arXiv 2026

MobilityBench: A Benchmark for Evaluating Route-Planning Agents in Real-World Mobility Scenarios

arXiv 2026

Thinking with Map: Reinforced Parallel Map-Augmented Agent for Geolocalization

arXiv 2026

MACE-Dance: Motion-Appearance Cascaded Experts for Music-Driven Dance Video Generation

arXiv 2026

Everything in Its Place: Benchmarking Spatial Intelligence of Text-to-Image Models

arXiv 2026

Code2World: A GUI World Model via Renderable Code Generation

arXiv 2026

Omni-WorldBench: Towards a Comprehensive Interaction-Centric Evaluation for World Models

arXiv 2026

LLaTiSA: Towards Difficulty-Stratified Time Series Reasoning from Visual Perception to Semantics

arXiv 2026

FLUX-Text: A Simple and Advanced Diffusion Transformer Baseline for Scene Text Editing

arXiv 2025

USP: Unified Self-Supervised Pretraining for Image Generation and Understanding

ICCV 2025

GPG: A Simple and Strong Reinforcement Learning Baseline for Model Reasoning

arXiv 2025

VMBench: A Benchmark for Perception-Aligned Video Motion Generation

ICCV 2025

Taming Hallucinations: Boosting MLLMs' Video Understanding via Counterfactual Video Generation

arXiv 2025

Tree Search for LLM Agent Reinforcement Learning

arXiv 2025

Advancing End-to-End Pixel Space Generative Modeling via Self-supervised Pre-training

arXiv 2025

From Editor to Dense Geometry Estimator

arXiv 2025

Omni-Effects: Unified and Spatially-Controllable Visual Effects Generation

arXiv 2025

UniVG-R1: Reasoning Guided Universal Visual Grounding with Reinforcement Learning

arXiv 2025

ImagerySearch: Adaptive Test-Time Search for Video Generation Beyond Semantic Dependency Constraints

arXiv 2025

S$^2$-Guidance: Stochastic Self Guidance for Training-Free Enhancement of Diffusion Models

arXiv 2025

MobileVLM V2: Faster and Stronger Baseline for Vision Language Model

arXiv 2024

MMGenBench: Evaluating the Limits of LMMs from the Text-to-Image Generation Perspective

arXiv 2024

LiDAR-PTQ: Post-Training Quantization for Point Cloud 3D Object Detection

arXiv 2024

VisionLLaMA: A Unified LLaMA Backbone for Vision Tasks

arXiv 2024

Adaptive Task Balancing for Visual Instruction Tuning via Inter-Task Contribution and Intra-Task Difficulty

arXiv 2024