Paper Archive

Mingwei Xu, Hao Fang 5/7/2026 arxiv

Reinforcement learning with verifiable rewards (RLVR), due to the deterministic verification, becomes a dominant paradigm for enhancing the reasoning ability of large language models (LLMs). The community witnesses the rapid change from the Proximal Policy Optimization (PPO) to Group Relative Policy...

Weiqing Xiao, Hong Li, Xiuyu Yang, Houyuan Chen, Wenyi Li, Tianqi Liu, Shaocong Xu, Chongjie Ye, Hao Zhao, Beibei Wang 5/7/2026 arxiv

Recent advances have shown that large-scale video diffusion models can be repurposed as neural renderers by first decomposing videos into intrinsic scene representations and then performing forward rendering under novel illumination. While promising, this paradigm fundamentally relies on accurate in...

Minbin Huang, Han Shi, Chuanyang Zheng, Yimeng Wu, Guoxuan Chen, Xintong Yu, Yichun Yin, Hong Cheng 5/7/2026 arxiv

Modern Mixture-of-Experts (MoE) architectures allocate expert capacity through a rigid per-layer rule: each transformer layer owns a separate expert set. This convention couples depth scaling with linear expert-parameter growth and assumes that every layer needs isolated expert capacity. However, re...

Omar El Khalifi, Thomas Rossi, Oscar Fossey, Thibault Fouque, Ulysse Mizrahi, Philip Torr, Ivan Laptev, Fabio Pizzati, Baptiste Bellot-Gurlet 5/7/2026 arxiv

For artistic applications, video generation requires fine-grained control over both performance and cinematography, i.e., the actor's motion and the camera trajectory. We present ActCam, a zero-shot method for video generation that jointly transfers character motion from a driving video into a new s...

Ryan Wang, Akshita Bhagia, Sewon Min 5/7/2026 arxiv

Large language models are typically deployed as monolithic systems, requiring the full model even when applications need only a narrow subset of capabilities, e.g., code, math, or domain-specific knowledge. Mixture-of-Experts (MoEs) seemingly offer a potential alternative by activating only a subset...

[object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object] 5/7/2026 huggingface

With the rapid evolution of foundation models, Large Language Model (LLM) agents have demonstrated increasingly powerful tool-use capabilities. However, this proficiency introduces significant security risks, as malicious actors can manipulate agents into executing tools to generate harmful content....

[object Object], [object Object], [object Object], [object Object], [object Object], [object Object] 5/7/2026 huggingface

Despite the growing popularity of Multimodal Domain Generalization (MMDG) for enhancing model robustness, it remains unclear whether reported performance gains reflect genuine algorithmic progress or are artifacts of inconsistent evaluation protocols. Current research is fragmented, with studies var...

[object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object] 5/7/2026 huggingface

Linear Attention (LA) offers a promising paradigm for scaling large language models (LLMs) to long sequences by avoiding the quadratic complexity of self-attention. Recent LA models such as Mamba2 and GDN interpret linear recurrences as closed-form online stochastic gradient descent (SGD), but naive...

[object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object] 5/7/2026 huggingface

Recent advances in generative video models are increasingly driven by post-training and test-time scaling, both of which critically depend on the quality of video reward models (RMs). An ideal reward model should predict accurate rewards that align with human preferences across diverse scenarios. Ho...

[object Object], [object Object], [object Object], [object Object], [object Object], [object Object] 5/7/2026 huggingface

Reinforcement learning fine-tuning has become the dominant approach for aligning diffusion models with human preferences. However, assessing images is intrinsically a multi-dimensional task, and multiple evaluation criteria need to be optimized simultaneously. Existing practice deal with multiple re...