Paper Archive

Zijian Zhang, Rizhen Hu, Athanasios Glentis, Dawei Li, Chung-Yiu Yau, Hongzhou Lin, Mingyi Hong 7/1/2026 arxiv

Reinforcement learning (RL) has become a central component of post-training large language models (LLMs), yet little is understood about how RL adaptation is distributed across transformer layers. Existing approaches typically update all model parameters uniformly, implicitly assuming that every lay...

Chih-Han Yang, Dai-Jie Wu, Yun-Ping Huang, Ping-Chun Hsieh, Kenneth Marino, Shao-Hua Sun 7/1/2026 arxiv

Prior work on imitation learning from suboptimal demonstrations typically relies on compressed supervision signals such as confidence estimates, discriminator scores, or importance weights. These scalar signals are inherently limited, as they cannot explicitly express intermediate reasoning about ta...

Shengguang Wu, Hao Zhu, Yuhui Zhang, Xiaohan Wang, Serena Yeung-Levy 7/1/2026 arxiv

Memory expertise is a learned skill: knowing what to encode, when to retrieve, and how to organize knowledge--a capacity known in cognitive science as metamemory. We bring this perspective to LLMs by treating memory management as a trainable skill. We promote file-system operations to first-class me...

Ben Slivinski, Michael Saldivar 7/1/2026 arxiv

When should an AI system's answer be trusted? Formal proof assistants offer certainty but cannot reach most of the problem distribution; scalar LLM judges offer coverage but produce opaque scores that cannot be audited after the fact and are subject to the same coherence issues as any LLM. We presen...

Yue Han, Chong Li, Zhening Liu, Cong Huang, Fang Deng, Yong Liu, Fangyun Wei, Yan Lu 7/1/2026 arxiv

Recent 3D generative models can synthesize high-quality geometry but often struggle to reproduce intricate textures from reference images, largely due to the scarcity of large-scale 3D training data with rich surface appearance. In contrast, visual generative models are trained on datasets several o...

Giovanni Monea, Nathan Godey, Kianté Brantley, Yoav Artzi 7/1/2026 arxiv

Transformers use the same forward computation stream to both predict the next token and store useful state for future token predictions. We formulate the \emph{state-prediction separation hypothesis}: disentangling the two roles yields better language modeling performance. We design a Transformer va...

Chenyang Ma, Yue Yang, Radu Corcodel, Siddarth Jain, Andrew Wu, Chiori Hori, Diego Romeres 7/1/2026 arxiv

Current work on robot furniture assembly mostly focuses on toy-scale settings or single-arm manipulation. We introduce FurnitureVLA, the first systematic study of real-scale bimanual furniture assembly using Vision-Language-Action models (VLAs). We formalize the task, develop a scalable simulation p...

Zhi Chen, Zhensu Sun, Yuling Shi, David Lo, Lingxiao Jiang 7/1/2026 arxiv

Repository-level performance-optimization benchmarks such as GSO, SWE-Perf and SWE-fficiency evaluate coding agents by applying patches to real repositories and comparing runtime against unoptimized baselines and official reference patches. Their leaderboard scores are increasingly used as evidence ...

Shayan Talaei, Abhinav Chinta, Devvrit Khatri, Amin Karbasi, Azalia Mirhoseini, Amin Saberi 7/1/2026 arxiv

Language models deployed in high-stakes roles can potentially favor certain entities, brands, or viewpoints, steering user decisions at scale. Such preferential biases can be introduced by any actor in the model's supply chain and are most dangerous when the model reveals its preference only on the ...

Anushrut Jignasu, Daniele Grandi 7/1/2026 arxiv

We present Linkify, a framework for learning from interface-augmented assembly graphs to enable context-aware part retrieval in mechanical assemblies. While recent generative AI methods for CAD have focused largely on isolated parts or monolithic assemblies, the rich geometric information at the int...