Tootfinder

KFFocus: Highlighting Keyframes for Enhanced Video Understanding
Ming Nie, Chunwei Wang, Hang Xu, Li Zhang
https://arxiv.org/abs/2508.08989 https://arxiv.o…

KFFocus: Highlighting Keyframes for Enhanced Video Understanding
Recently, with the emergence of large language models, multimodal LLMs have demonstrated exceptional capabilities in image and video modalities. Despite advancements in video comprehension, the substantial computational demands of long video sequences lead current video LLMs (Vid-LLMs) to employ compression strategies at both the inter-frame level (e.g., uniform sampling of video frames) and intra-frame level (e.g., condensing all visual tokens of each frame into a limited number). However, thi…

Michigan State University professor Josh Cowen announced Thursday that he is running for one of the battleground state’s most competitive congressional districts,
joining a crowded field of Democrats seeking to challenge Republican Rep. Tom Barrett.
In an interview with The Associated Press, Cowen said federal worker layoffs and cuts to research funding and Medicaid inspired him to run for the Lansing-area seat that Barrett flipped in 2024.
“What it really means in our daily…

Michigan State professor Josh Cowen announces run for US Rep. Tom Barrett's seat
A third Democrat has announced a bid to run against Michigan Republican U.S. Rep. Tom Barrett in one of the battleground state's most competitive districts. Josh Cowen is an education policy professor at Michigan State University known for his research on school voucher programs. He announced Thursday that he is running for the state's 7th Congressional District that encompasses the capital city of Lansing and surrounding rural areas. Barrett flipped the district in 2024, winning by 3.7 points …

A Case for Declarative LLM-friendly Interfaces for Improved Efficiency of Computer-Use Agents
Yuan Wang, Mingyu Li, Haibo Chen
https://arxiv.org/abs/2510.04607 https://

A Case for Declarative LLM-friendly Interfaces for Improved Efficiency of Computer-Use Agents
Computer-use agents (CUAs) powered by large language models (LLMs) have emerged as a promising approach to automating computer tasks, yet they struggle with graphical user interfaces (GUIs). GUIs, designed for humans, force LLMs to decompose high-level goals into lengthy, error-prone sequences of fine-grained actions, resulting in low success rates and an excessive number of LLM calls. We propose Goal-Oriented Interface (GOI), a novel abstraction that transforms existing GUIs into three decla…

LatentEvolve: Self-Evolving Test-Time Scaling in Latent Space
Guibin Zhang, Fanci Meng, Guancheng Wan, Zherui Li, Kun Wang, Zhenfei Yin, Lei Bai, Shuicheng Yan
https://arxiv.org/abs/2509.24771

LatentEvolve: Self-Evolving Test-Time Scaling in Latent Space
Test-time Scaling (TTS) has been demonstrated to significantly enhance the reasoning capabilities of Large Language Models (LLMs) during the inference phase without altering model parameters. However, existing TTS methods are largely independent, implying that LLMs have not yet evolved to progressively learn how to scale more effectively. With the objective of evolving LLMs to learn ``how to scale test-time computation,'' we propose LatentEvolve, a self-evolving latent TTS framework inspired by…

Do LLM Agents Know How to Ground, Recover, and Assess? A Benchmark for Epistemic Competence in Information-Seeking Agents
Jiaqi Shao, Yuxiang Lin, Munish Prasad Lohani, Yufeng Miao, Bing Luo
https://arxiv.org/abs/2509.22391

Do LLM Agents Know How to Ground, Recover, and Assess? A Benchmark for Epistemic Competence in Information-Seeking Agents
Recent work has explored training Large Language Model (LLM) search agents with reinforcement learning (RL) for open-domain question answering (QA). However, most evaluations focus solely on final answer accuracy, overlooking how these agents reason with and act on external evidence. We introduce SeekBench, the first benchmark for evaluating the \textit{epistemic competence} of LLM search agents through step-level analysis of their response traces. SeekBench comprises 190 expert-annotated trace…

When an LLM outputs, “I panicked”, it does not mean it panicked. It means that based on the preceding sentences, “I panicked” was a likely thing to come next.
It means it’s read a lot of fiction, in which drama is necessary.
It didn’t “panic”. It didn’t *anything*. It wrote a likely sequence of words based on a human request, which it then converted into code that matched those words somewhat. And a human, for some reason, allowed that code to be evaluated without oversight.

UltraEar: a multicentric, large-scale database combining ultra-high-resolution computed tomography and clinical data for ear diseases
Ruowei Tang, Pengfei Zhao, Xiaoguang Li, Ning Xu, Yue Cheng, Mengshi Zhang, Zhixiang Wang, Zhengyu Zhang, Hongxia Yin, Heyu Ding, Shusheng Gong, Yuhe Liu, Zhenchang Wang
https://arxiv.org/abs/2508.20141

UltraEar: a multicentric, large-scale database combining ultra-high-resolution computed tomography and clinical data for ear diseases
Ear diseases affect billions of people worldwide, leading to substantial health and socioeconomic burdens. Computed tomography (CT) plays a pivotal role in accurate diagnosis, treatment planning, and outcome evaluation. The objective of this study is to present the establishment and design of UltraEar Database, a large-scale, multicentric repository of isotropic 0.1 mm ultra-high-resolution CT (U-HRCT) images and associated clinical data dedicated to ear diseases. UltraEar recruits patients fro…

Morph: ChirpTransformer-based Encoder-decoder Co-design for Reliable LoRa Communication
Yidong Ren, Maolin Gan, Chenning Li, Shakhrul Iman Siam, Mi Zhang, Shigang Chen, Zhichao Cao
https://arxiv.org/abs/2507.22851

Morph: ChirpTransformer-based Encoder-decoder Co-design for Reliable LoRa Communication
In this paper, we propose Morph, a LoRa encoder-decoder co-design to enhance communication reliability while improving its computation efficiency in extremely-low signal-to-noise ratio (SNR) situations. The standard LoRa encoder controls 6 Spreading Factors (SFs) to tradeoff SNR tolerance with data rate. SF-12 is the maximum SF providing the lowest SNR tolerance on commercial off-the-shelf (COTS) LoRa nodes. In Morph, we develop an SF-configuration based encoder to mimic the larger SFs beyond S…

A CPFSK Transceiver with Hybrid CSS-DSSS Spreading for LPWAN PHY Communication
Wenkun Wen, Ruiqi Zhang, Peiran Wu, Tierui Min, Minghua Xia
https://arxiv.org/abs/2507.23029 https…

A CPFSK Transceiver with Hybrid CSS-DSSS Spreading for LPWAN PHY Communication
Traditional low-power wide-area network (LPWAN) transceivers typically compromise data rates to achieve deep coverage. This paper presents a novel transceiver that achieves high receiver sensitivity and low computational complexity. At the transmitter, we replace the conventional direct sequence spread spectrum (DSSS) preamble with a chirp spread spectrum (CSS) preamble, consisting of a pair of down-chirp and up-chirp signals that are conjugate to each other, simplifying packet synchronization.…

Hybrid Reward-Driven Reinforcement Learning for Efficient Quantum Circuit Synthesis
Sara Giordano, Kornikar Sen, Miguel A. Martin-Delgado
https://arxiv.org/abs/2507.16641

Hybrid Reward-Driven Reinforcement Learning for Efficient Quantum Circuit Synthesis
A reinforcement learning (RL) framework is introduced for the efficient synthesis of quantum circuits that generate specified target quantum states from a fixed initial state, addressing a central challenge in both the NISQ era and future fault-tolerant quantum computing. The approach utilizes tabular Q-learning, based on action sequences, within a discretized quantum state space, to effectively manage the exponential growth of the space dimension. The framework introduces a hybrid reward mecha…