13 papers
MeshOctave: Vertex Split-and-Rewire Cascades for Native Mesh Generation
Junkai Lin, Tianhao Zhao, Hang Long +10
Generating compact, artist-style meshes with explicit topology typically relies on autoregressive models which incur prohibitive sequential per-token costs, or continuous flow mode…
Influence-Directed Distillation: Solving the Diversity Bottleneck in Sampled-Token On-Policy Distillation
Run Yang, Runpeng Dai, Jie Sun +5
Sampled-token on-policy distillation (OPD) efficiently transfers capabilities from teacher to student using student-generated tokens, requiring teacher probabilities only for sampl…
MemeMind: Reference-Guided Trace Construction for Offline Context Optimization
Run Yang, Weihang Wang, Boheng Sheng +7
Offline context optimization improves an agent by revising its instructions and examples while keeping the model frozen. This approach learns from rollouts on an adaptation set, bu…
MemeBench: What LVLMs Miss When Interpreting Culture-Dependent Memes
Weihang Wang, Kainan Tu, Jielei Zhang +9
Large vision-language models have improved at describing visual content, but accurate descriptions do not ensure interpretation when meaning depends on knowledge beyond the pixels.…
SubdivAR: Autoregressive Next-Scale Prediction for Neural Mesh Subdivision
Huipeng Guo, Zikai Song, Hang Long +7
Mesh subdivision is a fundamental operation for converting coarse, editable meshes into high-resolution surfaces, with broad applications in digital asset creation. Classical rule-…
Large Language Model as Token Compressor and Decompressor
Wenbing Li, Yiran Wang, Zikai Song +4
In this paper, we study whether an off-the-shelf LLM can be adapted into a discrete, variable-length token compressor and decompressor for long-context processing. To this end, we…
Efficient Causal Structure Learning via Modular Subgraph Integration
Haixiang Sun, Pengchao Tian, Zihan Zhou +3
Learning causal structures from observational data remains a fundamental yet computationally intensive task, particularly in high-dimensional settings where existing methods face c…
Improving VQA Reliability: A Dual-Assessment Approach with Self-Reflection and Cross-Model Verification
Xixian Wu, Yang Ou, Pengchao Tian +4
Vision-language models (VLMs) have demonstrated significant potential in Visual Question Answering (VQA). However, the susceptibility of VLMs to hallucinations can lead to overconf…
MeshRipple: Structured Autoregressive Generation of Artist-Meshes
Junkai Lin, Hang Long, Huipeng Guo +8
Meshes serve as a primary representation for 3D assets. Autoregressive mesh generators serialize faces into sequences and train on truncated segments with sliding-window inference…
Diving into Mitigating Hallucinations from a Vision Perspective for Large Vision-Language Models
Weihang Wang, Xinhao Li, Ziyue Wang +5
Object hallucination in Large Vision-Language Models (LVLMs) significantly impedes their real-world applicability. As the primary component for accurately interpreting visual infor…
TextFlux: An OCR-Free DiT Model for High-Fidelity Multilingual Scene Text Synthesis
Yu Xie, Jielei Zhang, Pengyu Chen +5
Diffusion-based scene text synthesis has progressed rapidly, yet existing methods commonly rely on additional visual conditioning modules and require large-scale annotated data to…
MX-Font++: Mixture of Heterogeneous Aggregation Experts for Few-shot Font Generation
Weihang Wang, Duolin Sun, Jielei Zhang +1
Few-shot Font Generation (FFG) aims to create new font libraries using limited reference glyphs, with crucial applications in digital accessibility and equity for low-resource lang…
DNTextSpotter: Arbitrary-Shaped Scene Text Spotting via Improved Denoising Training
Yu Xie, Qian Qiao, Jun Gao +5
More and more end-to-end text spotting methods based on Transformer architecture have demonstrated superior performance. These methods utilize a bipartite graph matching algorithm…