arXiv 论文速递
Realistic and editable animal fur reconstruction from multi-view images is challenging due to fine-scale detail, self-occlusion and obfuscation, and, unlike human hair, the lack of…
· 2026-09-28
同一部署模型需服务多种算力预算，此前每种预算都要单独训练。该工作让单模型覆盖多预算，显著降低服务与压缩成本。
One deployed language model must often serve many compute budgets, yet serving each budget still means a separate training or compression run per point. We train a Telescopic Langu…
视频扩散模型需数十步去噪，推理成本极高。该工作改进分布匹配蒸馏，实现少步高质量视频生成，对视频生成落地意义重大。
Modern video diffusion models require tens of denoising evaluations over long spatiotemporal token sequences. Distribution Matching Distillation (DMD) reduces the number of functio…
Unified multimodal models can both look at and render images, so in principle they can repair their own generations: diagnose what an image gets wrong, revise it, observe the resul…
将多种分布匹配训练统一到一个框架，为一步视觉生成提供通用监督范式，有望大幅降低生成模型的采样开销。
\emph{Distributional training} provides collective supervision for one-step visual generation by matching real and generated features in frozen representation spaces. We introduce …
When a large language model (LLM) agent executes the same task, token consumption can vary by over an order of magnitude across runs. The agent chooses its next steps based on tool…
· 2026-09-28
We present a representation-learning framework for composite adaptive tracking control under dynamically coupled disturbances. The framework connects classical disturbance-accommod…
· 2026-09-28
We introduce Neural Harmonic Measure Operator (NHMO), a neural solver for elliptic PDE problems on variable-shape domains. The harmonic measure of a domain is the boundary probabil…
循环Transformer复用层以增算力，但如何与MoE结合尚不清晰。该工作给出循环MoE的设计原则，提升参数效率与扩展性。
Looped Transformers reuse one block of layers several times: by spending extra computation they push a model of fixed size further, and so use its parameters more fully; while spar…
智能体强化学习受限于超长上下文的显存瓶颈。该工作提出KV流式压缩方法，提升长程智能体训练的可扩展性。
Scaling the horizon of agentic LLMs is bottlenecked by the need to fit ever longer context traces in GPU memory. Context compaction has been the most popular mechanism to alleviate…
Looped transformers have demonstrated promising parameter efficiency by reusing layers for latent computation. Prior studies compare looped and non-looped models at matched paramet…
Linear Vision Transformers (ViTs) are designed to replace the attention in Softmax ViTs with the linear-complexity attention operator for more efficient token routing, but they req…