Paper Archive

Gongbo Zhang, Wen Wang, Ye Tian, Li Yuan 4/29/2026 arxiv

Diffusion large language models (dLLMs) offer parallel decoding and bidirectional context, but state-of-the-art dLLMs require billions of parameters for competitive performance. While existing distillation methods for dLLMs reduce inference steps within a single architecture, none address cross-arch...

Wanrong Zheng, Yunhao Ge, Laurent Itti 4/29/2026 arxiv

Breakthrough progress in vision-based navigation through unknown environments has been achieved by using multimodal large language models (MLLMs). These models can plan a sequence of motions by evaluating the current view at each time step against the task and goal given to the agent. However, curre...

Wenxuan Ye, Yangyang Zhang, Xueli An, Georg Carle, Yunpu Ma 4/29/2026 arxiv

Small language models (SLMs) offer computational efficiency for scalable deployment, yet they often fall short of the reasoning power exhibited by their larger counterparts (LLMs). To mitigate this gap, current approaches invoke an LLM to generate tokens at points of reasoning divergence, but these ...

Wanyue Zhang, Wenxiang Wu, Wang Xu, Jiaxin Luo, Helu Zhi, Yibin Huang, Shuo Ren, Zitao Liu, Jiajun Zhang 4/29/2026 arxiv

Vision-language models (VLMs) have shown strong performance on static visual understanding, yet they still struggle with dynamic spatial reasoning that requires imagining how scenes evolve under egocentric motion. Recent efforts address this limitation either by scaling spatial supervision with synt...

Junan Lin, Paul J. Goulart, Luca Furieri 4/29/2026 arxiv

The Alternating Direction Method of Multipliers (ADMM) is a widely used method for structured convex optimization, and its practical performance depends strongly on the choice of penalty and relaxation parameters. Motivated by settings such as Model Predictive Control (MPC), where one repeatedly sol...

Yeheng Chen, Chaoxiang Xie, Yuling Shi, Wenhao Zeng, Yongpan Wang, Hongyu Zhang, Xiaodong Gu 4/29/2026 arxiv

LLMs have achieved strong results on both function-level code synthesis and repository-level code modification, yet a capability that falls between these two extremes -- compositional code creation, i.e., building a complete, internally structured class from a specification -- remains underserved. C...

Steve Hanneke, Alkis Kalavasis, Shay Moran, Grigoris Velegkas 4/29/2026 arxiv

Learning curves are a fundamental primitive in supervised learning, describing how an algorithm's performance improves with more data and providing a quantitative measure of its generalization ability. Formally, a learning curve plots the decay of an algorithm's error for a fixed underlying distribu...

David Novikov, Eilon Vaknin, Narek Tumanyan, Mark Sheinin 4/29/2026 arxiv

The task of capturing and rendering 3D dynamic scenes from 2D images has become increasingly popular in recent years. However, most conventional cameras are bandwidth-limited to 30-60 FPS, restricting these methods to static or slowly evolving scenes. While overcoming bandwidth limitations is diffic...

Evangelia Kopadi, Dimitris Kalles 4/29/2026 arxiv

Can Neural Assemblies -- groups of neurons that fire together and strengthen through co-activation -- learn the direction of causal influence between variables? While established as a computationally general substrate for classification, parsing, and planning, neural assemblies have not yet been sho...

Zijie Wu, Chaohui Yu, Fan Wang, Xiang Bai 4/29/2026 arxiv

Recent advances in 4D content generation have attracted increasing attention, yet creating high-quality animated 3D models remains challenging due to the complexity of modeling spatio-temporal distributions and the scarcity of 4D training data. We present AnimateAnyMesh++, a feed-forward framework f...