Browse and export your curated research paper collection
[object Object], [object Object], [object Object], [object Object], [object Object] 11/13/2026 huggingface
multimodal learningSpeculative decoding accelerates generation by letting a lightweight drafter propose tokens for parallel verification by a target model. Diffusion drafters such as DFlash propose an entire token block in a single forward pass, but mainly focus on text-only tasks, leaving multimodal drafting underexp...
[object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object] 11/13/2026 huggingface
multimodal learningWe introduce Gamer, a generalist agent framework built for long-horizon tasks in complex interactive environments. Its end-to-end architecture combines perception, memory management, and multi-step reasoning. A shared training and deployment pipeline supports interaction with both conventional 2D gr...
[object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object] 11/13/2026 huggingface
roboticsThe release of GPT-6 Astra marks the emergence of a new paradigm in robotics: agentic robotics. Within weeks, frontier models with agentic harnesses matched or exceeded task-specific policies on many embodied benchmarks. Instead of training a dedicated policy for each family of tasks, an agentic rob...
[object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object] 11/13/2026 huggingface
natural language processingText-to-SQL systems translate natural language questions into SQL queries over increasingly complex databases. However, widely used benchmarks evaluate questions independently, overlooking settings where earlier queries over the same database can supply joins or calculations for a new question. We i...
[object Object] 11/13/2026 huggingface
machine learningWe present Tessa, a hardware-aware, device-wide scheme to encode classical data on quantum computers. We use it to experimentally encode and decode up to 1568 real values using IBM's Phoenix and Fez quantum computers on a variety of data. Tessa's construction is an extension of QPIXL and QCrank. How...
Jianjun Zhou, Hua Geng, Haoyu Guo 11/13/2026 arxiv
generative modelsDirect diffusion modeling of high-dimensional raw video data is challenging, and existing pixel-space methods often rely on specialized architectures. We introduce JVT (Just Video Transformer), a simple large-patch DiT-style Transformer for pixel-space video diffusion, without a pretrained autoencod...
Jonathan D. McCart, Pranav I. Deevi, Mehdi Azabou, Nanda H. Krishna, Caleb A. McKinney, Nicholas S. Card, Sergey D. Stavisky, Chethan Pandarinath 11/13/2026 arxiv
machine learningRecent advances in speech neuroprostheses have enabled new communication avenues for people who have lost the ability to speak due to neurological illness or injury. These systems can decode neural activity during attempted speech into text by relying on language priors to achieve high decoding accu...
Aayush Marasini, Barsat Khadka, Nick Rahimi 11/13/2026 arxiv
machine learningRecent work shows that large language models (LLMs) can operate directly on the parameters of other neural networks. They can read what a network was trained to do, fix a network that fails, and write working networks from scratch, all without gradient descent. This capability has been termed Weight...
Jiaming Tang, Zhuoyang Zhang, Junxian Guo, Fangzhou Zhao, Yilong Zhao, Zekai Li, Xingyang Li, Yuyang Zhao, Song Bian, Zhijian Liu, Song Han 11/13/2026 arxiv
roboticsRobot-use agents (RUAs) have emerged as a promising approach to general-purpose robot control. However, strong performance has so far been achieved only by frontier proprietary models such as GPT-6 Astra and Claude Fable 5.2, whereas open-weight models remain substantially less capable. We show that...
Tony H. Zhang, Connor Mattson, Daniel S. Brown 11/13/2026 arxiv
reinforcement learningDemonstrations are an effective way to accelerate single-agent reinforcement learning (RL), but extending this idea to multi-agent reinforcement learning (MARL) is non-trivial as it is difficult and often impossible for a single person to teleoperate multiple agents simultaneously. Round-Robin Behav...
Preparing your export...