The list as it stood that day: the papers researchers were upvoting on Hugging Face's daily papers. Papers stay on arXiv.
We observe that critic values vary primarily across turns, motivating optimization anchored at turns with finer credit allocation among tokens.
Tao Ren, Hui Yang, Jia Deng and 16 moreStreaming audio-visual target speaker extraction (AVTSE) is essential for latency-sensitive applications.
Wendi Sang, Kai Li, Yifan Li and 2 moreIn this work, we develop this measure-based view of benchmark evaluation. This perspective allows us to identify and formalize two central failure modes: measure mismatch, where the benchmark difficulty distribution differs from the intended difficulty distribution, and coverage…
Yifan Sun, Naicheng Yu, Jiawen Gong and 2 moreGenerating videos of a specific subject from a few reference images remains challenging when the camera reveals surfaces that are not visible in the input.
Junyeong Ahn, Geonwoo Kim, Kinam Kim and 4 moreWe address these two questions separately: training dynamics determine when to acquire new experience, while the answers to new tasks remain independently checkable.
Yu Liu, Youxing Li, Yuedong Tan and 17 moreWe present EmbeddingGemma 2, an open multimodal embedding model which natively represents text, images, audio, video, and combinations thereof in a unified space.
Henrique Schechter Vera, Sahil Dua, Jovan Andonov and 70 moreWe ask whether motion trajectories form another such modality: as embodied models become more capable, should their sensory representations converge toward the structure of physical motion?
Yunfei Xie, Howard H. Qian, Shiyi Lan and 2 moreWe propose WorkFactory, a scalable framework for constructing coherent and executable professional tasks.
Ziyang Zeng, Tingyang Chen, Jia Deng and 10 moreTo bridge this gap, we present TAO, a tool-aware joint scheduling framework for LLM-based agentic serving.
Shuhuai Li, Shengdong Ye, Dongdong Ge and 2 moreWe study this question with h1, a simple harness that gives a model an efficient interface to Lean 4 and keeps it working through verifier feedback and self-reflection, without imposing a decomposition or search structure. h1 reaches state-of-the-art results on PutnamBench…
Skander Moalla, Ahmad Rammal, Niket Patel and 2 moreLocating relevant evidence in long inputs is a core capability of Multimodal Large Language Models.
Jia Wang, Yuqing Li, Jiangnan Li and 2 moreIn this paper, we present REALCLI, a paired benchmark that unifies the evaluation of task execution and human-agent collaboration quality on realistic CLI tasks.
Yunqi Liu, Peiyu Wang, Bingli Wang and 21 moreWe introduce VibeGame, a framework for creating complete 2D game projects from natural-language prompts and optional reference images.
Wenbo Hu, Ken Li, Jiazhe Wei and 13 moreWe address this gap with WeVisCut, a long-form script-to-video system that connects tool execution with policy learning.
Chenyu Mu, Wenming Weng, Qinrui Wang and 8 moreSince visual tokens make up 89-97% of this input on the benchmarks we study, most of the decoding computation is spent repeatedly processing the same image.
Donghyeon Cho, Joowon Kim, Seungho Shin and 1 moreWe introduce Co-Design Bench, a reference-free benchmark of 273 tasks curated from 37,463 deduplicated queries across 26,314 real user coding sessions.
Xilin Wei, Shengyuan Ding, Xinyu Fang and 13 moreWe introduce PersonaCUABench, which holds 74 tasks across 11 domains fixed and varies only who asks.
Haoming Li, Defu Cao, Xu Hu and 23 moreTo this end, we present IntReal, comprising two complementary components: IntReal-100K, a real-world dataset of multimodal interleaved samples spanning four major categories, and the IntReal Evaluation Suite, which evaluates model performance across seven complementary…
Shaohan Yu, Jie Qin, Wende Tan and 4 moreWe show that coarse second-order image statistics can ease this task: frozen Wiener estimates improve velocity learning, with gains extending beyond the linear predictions they explicitly provide.
Ziqiao Wang, Yang YouMany Indian banks serve customers through FAQ pages and scripted chatbots. Assistants based on language models could respond faster and carry out requests such as blocking a card, but only if they give correct information and follow the bank's rules.
Krishanu Adhikary, Prashant Devadiga