Paper Archive

Runhui Huang, Qihui Zhang, Zhe Liu, Yu Gao, Jie Wu, Hengshuang Zhao 7/13/2026 arxiv

In this paper, we propose SpectraReward, a training-free reward function that turns pretrained MLLMs into off-the-shelf reward models for image-generation reinforcement learning. Instead of asking the MLLM to judge a generated image or answer decomposed verification questions, SpectraReward measures...

Daniel Garibi, Ronen Kamenetsky, Hadar Averbuch-Elor, Daniel Cohen-Or, Or Patashnik 7/13/2026 arxiv

Generating and editing a person's face demands high precision, as even minor modifications can significantly alter a subject's perceived identity. Current personalization and editing methods built on general-purpose text-to-image models, however, often lack the precision required for fine-grained fa...

Dian Wang, Jisang Park, Xiaomeng Xu, Han Zhang, Shuran Song, Jeannette Bohg 7/13/2026 arxiv

Robotic manipulation is inherently multi-frame: local actions may be simple in an end-effector frame, while transport, upright-object handling, and whole-body coordination are better represented in a base-aligned frame. However, modern diffusion-based visuomotor policies typically commit to a single...

Shikai Qiu, Marc Finzi, Yujia Zheng, Kun Zhang, Andrew Gordon Wilson 7/13/2026 arxiv

Compression is fundamental to intelligence. A model that can represent its training data as a short code has discovered regularities that enable generalization. Large neural networks may learn functions far simpler than their parameter counts suggest, but it is challenging to construct codes that re...

Gabrielle Kaili-May Liu, Areeb Gani, Jacqueline Lu, Jordan Thomas, Mark Steyvers, Arman Cohan 7/13/2026 arxiv

Metacognition is a foundational component of intelligence critical to effective learning, problem solving, decision-making, communication, and more. In recent years, it has become increasingly recognized as a cornerstone of capable, transparent AI systems. Yet while LLMs have made significant progre...

Tiberiu Musat, Tiago Pimentel, Nicholas Zucchet, Thomas Hofmann 7/13/2026 arxiv

We present a theoretical framework to explain the emergence of inductive reasoning abilities in Transformer language models. While previous works on Transformer learning dynamics have so far been mostly tied to specific tasks, we study a generalized class of inductive tasks that unifies several synt...

Yunhai Feng, Natalie Leung, Jiaxuan Wang, Lujie Yang, Haozhi Qi, Preston Culbertson 7/13/2026 arxiv

Recent work in humanoid whole-body control has found success with a simple recipe: retarget human motion to robot kinematic references, then train policies via reinforcement learning (RL) to track them. But how does this recipe transfer to dexterous manipulation? The answer is not obvious, as manipu...

Zixiang Xu, Sixian Li, Huaxing Liu, Xiang Wang, Shuai Li, Zirui Song, Xiuying Chen 7/13/2026 arxiv

Existing studies of LLM-as-judge scoring bias work predominantly at the input-output level: they perturb inputs, measure score deltas, and propose prompt-level mitigations. We argue that the same biases admit a representation-level account in the judge's hidden state, complementary to the input-outp...

Shijie Wang, Honglu Zhou, Ziyang Wang, Ran Xu, Caiming Xiong, Silvio Savarese, Chen Sun, Juan Carlos Niebles 7/13/2026 arxiv

Current Video Large Language Models (Video LLMs) excel in question answering (QA) but largely operate as black boxes, providing textual answers without verifiable visual grounding. Existing explainability efforts rely on textual rationales or sparse bounding boxes, which struggle to capture complex ...

Deniz Kerimoglu, Junnosuke Kamohara, Jiyeon Maeng, Ziwon Yoon, Seth Hutchinson, Ye Zhao, Daniel I. Goldman 7/13/2026 arxiv

Bipedal robots are challenging to control because they operate close to instability, where small variations in foot-terrain contact can rapidly destabilize locomotion. On rigid terrain, bipedal robots mitigate this fragility by using well-established contact mechanics and control strategies. On flow...