Paper Archive

Junhwa Hur, Charles Herrmann, Songyou Peng, Philipp Henzler, Zeyu Ma, Todd Zickler, Deqing Sun 2/27/2026 arxiv

Dense 4D reconstruction from unposed images remains a critical challenge, with current methods relying on slow test-time optimization or fragmented, task-specific feedforward models. We introduce UFO-4D, a unified feedforward framework to reconstruct a dense, explicit 4D representation from just a p...

Shengqu Cai, Weili Nie, Chao Liu, Julius Berner, Lvmin Zhang, Nanye Ma, Hansheng Chen, Maneesh Agrawala, Leonidas Guibas, Gordon Wetzstein, Arash Vahdat 2/27/2026 arxiv

Scaling video generation from seconds to minutes faces a critical bottleneck: while short-video data is abundant and high-fidelity, coherent long-form data is scarce and limited to narrow domains. To address this, we propose a training paradigm where Mode Seeking meets Mean Seeking, decoupling local...

Fan Shu, Yite Wang, Ruofan Wu, Boyi Liu, Zhewei Yao, Yuxiong He, Feng Yan 2/27/2026 arxiv

The fast-growing demands in using Large Language Models (LLMs) to tackle complex multi-step data science tasks create an emergent need for accurate benchmarking. There are two major gaps in existing benchmarks: (i) the lack of standardized, process-aware evaluation that captures instruction adherenc...

Jenny Y. Huang, Leshem Choshen, Ramon Astudillo, Tamara Broderick, Jacob Andreas 2/27/2026 arxiv

Multi-turn interactions with large language models typically retain the assistant's own past responses in the conversation history. In this work, we revisit this design choice by asking whether large language models benefit from conditioning on their own prior responses. Using in-the-wild, multi-tur...

Weinan Dai, Hanlin Wu, Qiying Yu, Huan-ang Gao, Jiahao Li, Chengquan Jiang, Weiqiang Lou, Yufan Song, Hongli Yu, Jiaze Chen, Wei-Ying Ma, Ya-Qin Zhang, Jingjing Liu, Mingxuan Wang, Xin Liu, Hao Zhou 2/27/2026 arxiv

GPU kernel optimization is fundamental to modern deep learning but remains a highly specialized task requiring deep hardware expertise. Despite strong performance in general programming, large language models (LLMs) remain uncompetitive with compiler-based systems such as torch.compile for CUDA kern...

Zhengbo Wang, Jian Liang, Ran He, Zilei Wang, Tieniu Tan 2/27/2026 arxiv

Modern optimizers like Adam and Muon are central to training large language models, but their reliance on first- and second-order momenta introduces significant memory overhead, which constrains scalability and computational efficiency. In this work, we reframe the exponential moving average (EMA) u...

Shruti Joshi, Théo Saulus, Wieland Brendel, Philippe Brouillard, Dhanya Sridhar, Patrik Reizinger 2/27/2026 arxiv

Identifiability in representation learning is commonly evaluated using standard metrics (e.g., MCC, DCI, R^2) on synthetic benchmarks with known ground-truth factors. These metrics are assumed to reflect recovery up to the equivalence class guaranteed by identifiability theory. We show that this ass...

Amir Asiaee 2/27/2026 arxiv

Neural networks are hypothesized to implement interpretable causal mechanisms, yet verifying this requires finding a causal abstraction -- a simpler, high-level Structural Causal Model (SCM) faithful to the network under interventions. Discovering such abstractions is hard: it typically demands brut...

Arnas Uselis, Andrea Dittadi, Seong Joon Oh 2/27/2026 arxiv

Compositional generalization, the ability to recognize familiar parts in novel contexts, is a defining property of intelligent systems. Although modern models are trained on massive datasets, they still cover only a tiny fraction of the combinatorial space of possible inputs, raising the question of...

Ali Behrouz, Zeman Li, Yuan Deng, Peilin Zhong, Meisam Razaviyayn, Vahab Mirrokni 2/27/2026 arxiv

Transformers have been established as the de-facto backbones for most recent advances in sequence modeling, mainly due to their growing memory capacity that scales with the context length. While plausible for retrieval tasks, it causes quadratic complexity and so has motivated recent studies to expl...