Paper Archive

Susung Hong, Brian Curless, Ira Kemelmacher-Shlizerman, Steve Seitz 3/11/2026 arxiv

We propose a fully automated AI system that produces short comedic videos similar to sketch shows such as Saturday Night Live. Starting with character references, the system employs a population of agents loosely based on real production studio roles, structured to optimize the quality and diversity...

Tao Zhong, Yixun Hu, Dongzhe Zheng, Aditya Sood, Christine Allen-Blanchette 3/11/2026 arxiv

We propose Neural Field Thermal Tomography (NeFTY), a differentiable physics framework for the quantitative 3D reconstruction of material properties from transient surface temperature measurements. While traditional thermography relies on pixel-wise 1D approximations that neglect lateral diffusion, ...

Yan-Bo Lin, Jonah Casebeer, Long Mai, Aniruddha Mahapatra, Gedas Bertasius, Nicholas J. Bryan 3/11/2026 arxiv

Generating music that temporally aligns with video events is challenging for existing text-to-music models, which lack fine-grained temporal control. We introduce V2M-Zero, a zero-pair video-to-music generation approach that outputs time-aligned music for video. Our method is motivated by a key obse...

Shuyao Shang, Bing Zhan, Yunfei Yan, Yuqi Wang, Yingyan Li, Yasong An, Xiaoman Wang, Jierui Liu, Lu Hou, Lue Fan, Zhaoxiang Zhang, Tieniu Tan 3/11/2026 arxiv

We propose DynVLA, a driving VLA model that introduces a new CoT paradigm termed Dynamics CoT. DynVLA forecasts compact world dynamics before action generation, enabling more informed and physically grounded decision-making. To obtain compact dynamics representations, DynVLA introduces a Dynamics To...

Ezequiel Lopez-Rubio, Mario Pascual-Gonzalez 3/11/2026 arxiv

We present IsalGraph, a method for representing the structure of any finite, simple graph as a compact string over a nine-character instruction alphabet. The encoding is executed by a small virtual machine comprising a sparse graph, a circular doubly-linked list (CDLL) of graph-node references, and ...

Mingyang Song, Mao Zheng, Chenning Xu 3/11/2026 arxiv

The paradigm of LLM-as-a-judge relies on a critical assumption, namely that high inter-evaluator agreement indicates reliable and objective evaluation. We present two complementary findings that challenge this assumption. \textbf{First}, we demonstrate that this consensus is frequently illusory. We ...

Tycho F. A. van der Ouderaa, Mart van Baalen, Paul Whatmough, Markus Nagel 3/11/2026 arxiv

Scalar quantization of large language models (LLMs) is fundamentally limited by information-theoretic bounds. While vector quantization (VQ) overcomes these limits by encoding blocks of parameters jointly, practical implementations must avoid the need for expensive lookup mechanisms or other explici...

Nour Jedidi, Jimmy Lin 3/11/2026 arxiv

Pseudo-relevance feedback (PRF) methods built on large language models (LLMs) can be organized along two key design dimensions: the feedback source, which is where the feedback text is derived from and the feedback model, which is how the given feedback text is used to refine the query representatio...

Patricia Paskov, Kevin Wei, Shen Zhou Hong, Dan Bateyko, Xavier Roberts-Gaal, Carson Ezell, Gailius Praninskas, Valerie Chen, Umang Bhatt, Ella Guest 3/11/2026 arxiv

Human uplift studies - or studies that measure AI effects on human performance relative to a status quo, typically using randomized controlled trial (RCT) methodology - are increasingly used to inform deployment, governance, and safety decisions for frontier AI systems. While the methods underlying ...

Theo Schwider, Ramin Ramezani 3/11/2026 arxiv

Single-cell electrophysiological recordings provide a powerful window into neuronal functional diversity and offer an interpretable route for linking intrinsic physiology to transcriptomic identity. Here, we replicate and extend the electrophysiology-to-transcriptomics framework introduced by Gouwen...