arxiv
Score 21.4
2026-09-23 · Niklas Scholz, David Thulke, Abdallah Nasir, Will Allred, Evgeny Matusov, Hermann Ney
Research Track A · General AI
Fine-tuning large language models on parallel data improves translation quality but can cause catastrophic forgetting. Mitigation methods are generally evaluated by retention on general benchmarks. We ask whether these findings transfer to machine translation (MT) fine-tuning and to MT-specific instruction following (M…
- Review
- pending
- Role
- unreviewed
- Read
- now
arxiv
Score 21.2
2026-09-24 · Arunabh Srivastava, Mohammad A., Khojastepour, Srimat Chakradhar, Sennur Ulukus
General AI
Large Language Models (LLMs) typically exhibit a performance profile where reliability degrades as task complexity increases. We address the challenge of generating high-quality natural language executable plans for complex tasks by introducing $\textbf{GRASP}$, a strategy-aware, multi-stage planning framework. GRASP d…
- Review
- pending
- Role
- unreviewed
- Read
- now
arxiv
Score 20.4
2026-09-23 · Chengguang Gan, Yunhao Liang, QingHao Zhang, Shiwen Ni
Research Track B · General AI
Web agents are usually evaluated in live environments, where environment state and judge models drift between runs, so the same checkpoint rarely reproduces the same score, making controlled studies of training phenomena impractical. We present WebMRE, an offline benchmark of 541 tasks and 5,293 steps derived from succ…
- Review
- pending
- Role
- unreviewed
- Read
- now
arxiv
Score 18.2
2026-09-24 · Jordan L. Cahoon, Chloe O. Stanwyck, Sulaiman Somani, Philip Chung, Kevin R Keet, Kameron C. Black, Andrea T. Fisher, Sarita Khemani, Jerry Liu, Stephen Ma, Saloni K. Maharaj, Rita M. Pandya, Eduardo Perez-Guerrero, Priyanka Pillai, Lisa Shieh, David J. H. Wu, James Xie, James C. McAvoy, Teresa Nguyen, Jessica Tran, Lucy Yin, Bridget Lin, Alison Callahan, Jason A. Fries, Nigam H. Shah, Emily Alsentzer
General AI
Large language model (LLM)-based clinical assistants are increasingly being integrated into electronic health record (EHR) systems, transforming how clinicians retrieve and synthesize information from patient records. Their safety and utility depend on rigorous evaluation, yet existing benchmarks are manually curated, …
- Review
- pending
- Role
- unreviewed
- Read
- now
arxiv
Score 18.2
2026-09-24 · Sunli Chen, Ding Zhong, Ziqiao Ma, Jiaxin Liu, Zeyuan Yang, Hao Zhang, Lie Lu, Joyce Chai, Chuang Gan
General AI
Current vision-language models (VLMs) excel at visual content understanding and text-based reasoning, yet their structure limits the advancement of incorporating images into the reasoning chain. Though Omnimodal models have made efforts in unifying text and image generation, they focus on visual tasks in the open-domai…
- Review
- pending
- Role
- unreviewed
- Read
- now
arxiv
Score 18.2
2026-09-24 · Yehang Zhang, Haojian Huang, Yifan Chang, Jianchong Su, Bohan Zhou, Yingjie Xu, Wosong Chen, Tianhao Zhou, Chenxu Wang, Tianyi Zhang, Yangkai Wei, Wenqian Li, Shiyuan Deng, Yinchuan Li, Ying-Cong Chen, Zexi Li
General AI
General-purpose vision-language models (VLMs) bring broad knowledge and spatial reasoning to robot manipulation, yet existing systems either use them indirectly, to predict constraints or write programs, or give them a view of the scene rather than a world in which to act. We present World Action Agent (WAA), a multi-a…
- Review
- pending
- Role
- unreviewed
- Read
- now
huggingface
Score 17.4
2026-09-24 · Xingyu Wu, Yuchen Yan, Zhengxi Lu, Siqi Chen, Xin ZHANG, Aiting Liu, Chao Deng, Jie Liu, Jin Ma, Jian Shao, Jun Xiao, Yongliang Shen
General AI
Deep search requires LLM agents to decompose complex queries, search for evidence, and synthesize grounded answers, yet existing ReAct-style agents suffer from two limitations: role coupling, where one policy must handle planning, evidence use, and synthesis; and context accumulation, where growing search histories int…
- Review
- pending
- Role
- unreviewed
- Read
- now
arxiv
Score 17.2
2026-09-22 · Laizhen Li, Jiarui Li, Juanjuan Zhao, Kejiang Ye, Ye Li, Cheng-zhong Xu, Xitong Gao
Research Track B · General AI
Large language model (LLM) agents often handle streams of related tasks, yet standard harnesses repeatedly ask the model to reconstruct the same control decisions inside each task's context. We study whether task feedback can instead turn recurring control into reusable executable code, while reserving LLM calls for ta…
- Review
- pending
- Role
- unreviewed
- Read
- now
arxiv
Score 17.2
2026-09-24 · Edesio Alcoba, Kevin Rossell, Aman Gupta, Shao Tang, Jiwoo Hong, Pabel Carrillo-Mendoza, Wanderson Conceição Ferreira, Alvaro Tedeschi, Zayd Simjee, Shreya Rajpal, Bruno Finardi Hime, Christian Sousa, Luis Moneda, Herbert Fei, Daniel Silva, Rohan Ramanath
General AI
Customer experience (CX) agents use tools and large language models to address customer requests and guide conversational interactions with an organization's products. Improving these agents, especially in regulated industries, is difficult: they must detect intent, follow complex operational policies and use tools rel…
- Review
- pending
- Role
- unreviewed
- Read
- now
arxiv
Score 16.9
2026-09-24 · Linghua Zhang
Research Track B · General AI
Vision-language models (VLMs) have become a common foundation for autonomous mobile GUI agents, but most existing systems rely on the VLM for both planning and action grounding at nearly every interaction step, leading to substantial latency and model-serving cost. We introduce Jev-Mobile, which shifts this paradigm to…
- Review
- pending
- Role
- unreviewed
- Read
- now
arxiv
Score 16.2
2026-09-24 · Debajyoti Mazumder, Mamta, Abhirama Subramanyam Penamakuri
General AI
Online misinformation increasingly appears in spoken formats such as news clips, podcasts, interviews, political speeches, and social media videos, creating a need for fact-checking systems that can verify claims directly from speech. We introduce VeriSpeak, a probe benchmark for studying speech-based fact verification…
- Review
- pending
- Role
- unreviewed
- Read
- now
huggingface
Score 15.4
2026-09-20 · Ruixun Liu, Yuxuan Wang, Jiacheng Xie, Yuhuan You, Donghua Cai, Junming Lin, Xiong-Hui Chen, Zhifang Guo, Yunfei Chu, Qize Yang, Xize Cheng, Jin Xu, Yiwu Zhong
General AI
Humans can effortlessly localize the direction of a sound source and integrate it with visual cues for reasoning, yet this remains challenging for embodied agents. In particular, it is still unclear how to effectively evaluate and model spatial audio understanding in embodied settings. To address this gap, we introduce…
- Review
- pending
- Role
- unreviewed
- Read
- now
arxiv
Score 15.2
2026-09-24 · Xueshu Chen, Yan Wang, Zihao Xue, Jiefu Li, Zhenfang Liu, Jayden Chen, Zhen Bi, Jungang Lou
General AI
Long-horizon tasks require preserving and later recovering cross-session evidence under a bounded, query-blind memory budget. Existing compression can discard fine-grained visual cues or conflate semantically similar but incompatible observations. We present C3M, a cross-session multimodal memory organization that main…
- Review
- pending
- Role
- unreviewed
- Read
- now
arxiv
Score 15.2
2026-09-24 · Matteo Merler, Bowen Li, Josh Roy, Yichao Liang, Qianwei Wang, Yixuan Huang, Tom Silver
General AI
Task and motion planning (TAMP) problems remain difficult even with full observability and object-centric states because discrete decisions are tightly coupled to geometric, kinematic, and dynamic constraints. Generalized TAMP addresses this difficulty by exploiting regularities across problem instances to reduce plann…
- Review
- pending
- Role
- unreviewed
- Read
- now
arxiv
Score 15.2
2026-09-24 · David Schmotz, Derck Prinzhorn, Luca Beurer-Kellner, Anselm Paulus, Ameya Prabhu, Maksym Andriushchenko
General AI
A central concern in AI safety is that agents may treat oversight as an obstacle when it conflicts with completing their goals. We study instrumental evasion, the propensity of LLM agents to circumvent runtime monitoring as a means of completing ordinary tasks. We introduce EvasionBench, a benchmark of 50 diverse task-…
- Review
- pending
- Role
- unreviewed
- Read
- now
arxiv
Score 14.4
2026-09-21 · Hongwei Yan, Kanglei Zhou, Qi Cheng, Weiyi Dong, Chunyan Lan, Guanglong Sun, Jun Zhou, Qian Li, Yi Zhong, Liyuan Wang
Research Track A · General AI
Continual learning, the ability to learn from sequential experience while retaining and adapting prior knowledge, is central to intelligent systems operating in changing environments. However, conventional continual learning is typically studied with offline task-wise training and clear task boundaries, leaving a subst…
- Review
- pending
- Role
- unreviewed
- Read
- now
huggingface
Score 14.4
2026-09-24 · Zhiyu Xu, Weilong Yan, Yufei Shi, Shiyang Li, Yihao Liu, Kin-Man Lam, Yuewen Cao
General AI
Recent years have witnessed major progress in joint audio-video generation. Existing models still suffer from limited per-modality fidelity, insufficient text-modality alignment and weak cross-modal synchronization. While reinforcement-learning post-training offers a promising remedy, directly adapting it to joint audi…
- Review
- pending
- Role
- unreviewed
- Read
- now
arxiv
Score 14.4
2026-09-24 · Siyuan Luo, Yang Xiao, Ting Dang
Research Track A
Audio classification is inherently a multi-label task, as real-world acoustic environments contain multiple simultaneous sound events. When new sound classes emerge, models must incorporate them without forgetting previously learned ones: a challenge known as class-incremental learning. Existing methods rely on storing…
- Review
- pending
- Role
- unreviewed
- Read
- now
huggingface
Score 14.4
2026-09-24 · Beomsoo Kim, Byeongju Kim, Dohyun Kim, Dongwon Kim, Eunchong Kim, Hongmin Kim, Hyeojung Im, Hyeonbin Hwang, Hyeonghwan Kim, Hyoseok Seol, Insub Im, Irene Chen, Jaeseung Jeon, Jimin Hong, Kiyoon Yoo, Minkyoung Park, Seohyeon Jung, Seungjun Chung, Sue Hyun Park, Sungwoo Kim, Youngin Cho, Yujeong Son, Kangwook Lee, Hyunseung Kim
General AI
We introduce PUBG Ally, an embodied agent for PUBG: BATTLEGROUNDS that can reason, act autonomously, and play alongside players as a voice-enabled teammate. Building such a teammate requires combining two difficult capabilities: it must perceive and respond to a constantly changing game world under strict latency const…
- Review
- pending
- Role
- unreviewed
- Read
- now
arxiv
Score 14.2
2026-09-24 · S. Talha Bukhari, Austin Garrett, Yi Wei, Ruiqi Ni, Zachary Kingston, Aniket Bera
General AI
Visuomotor policies learn a direct map from raw sensory observations to robot action sequences. Policies based on Diffusion and Flow Matching capture the multimodal distribution over action sequences in an end-to-end manner. This expressivity comes at the cost of multi-step numerical integration of the learned vector f…
- Review
- pending
- Role
- unreviewed
- Read
- now
arxiv
Score 14.2
2026-09-24 · Nayoung Choi, Shengjian Chen, Xiaokai Wei, Wenzheng Zhang, Daiyao Yi, Rachit Pareek, Vincent Su, Michelle Gong, Jinho D. Choi
General AI
Query understanding (QU) plays a critical role in production search systems, translating raw user queries into search execution plans that drive downstream retrieval and ranking. While large language models (LLMs) have enabled QU to be framed as a structured multi-task generation problem (e.g., intent classification, q…
- Review
- pending
- Role
- unreviewed
- Read
- now
huggingface
Score 14.0
2026-08-29 · Zhenhua Zou, Sheng Guo, Qiuyang Zhan, Lepeng Zhao, Shuo Li, Zhuotao Liu
General AI
Modern AI agents routinely cross trust boundaries: they ingest untrusted content, combine it with privileged instructions, persist intermediate beliefs in long-term memory, and invoke privileged tools. This creates an attack surface in which malicious payloads can enter through model inputs and cause harmful tool actio…
- Review
- pending
- Role
- unreviewed
- Read
- now
arxiv
Score 13.2
2026-09-24 · Lior Biton, Oren Tsur
General AI
Conspiratorial discourse on social media is not always expressed through explicit claims or stable lexical markers. The same surface content may express endorsement, legitimate concerns, criticism, satire, or mockery. The main challenge is therefore not only recognizing conspiracy-related claims, but inferring the spea…
- Review
- pending
- Role
- unreviewed
- Read
- now
arxiv
Score 13.2
2026-09-24 · Yuyao Liu, Jiayuan Mao, David Hsu, Leslie Pack Kaelbling, Tomás Lozano-Pérez
General AI
Coding agents have demonstrated enormous success in solving complex programming problems. To leverage their potential for robot systems, this work introduces Robot Agentic Programming from Demonstrations (RAPID), which automatically generates, verifies, and refines robot programs, given a single visual human demonstrat…
- Review
- pending
- Role
- unreviewed
- Read
- now
arxiv
Score 13.2
2026-09-24 · Xinyue Zeng, Jiawei Zhang, Yujun Yan, Dawei Zhou
General AI
Long-horizon reasoning remains a central challenge for large language models (LLMs) under sparse-reward regimes. We argue that this brittleness arises from two biases induced by complex reasoning spaces: an exploration bias, where models are drawn toward locally plausible but structurally unstable branches, and a compo…
- Review
- pending
- Role
- unreviewed
- Read
- now
arxiv
Score 12.4
2026-09-22 · Trang Nguyen, Eulrang Cho, Bingqing Chen, Tim Dettmers
Research Track A · General AI
Agents often work on complex problems that require millions of tokens of context, which necessitates compacting across sessions due to limited context windows. We develop CliffCompaction, an autocompaction technique that reduces cost by up to 50% under a bounded context while maintaining or improving performance on Ter…
- Review
- pending
- Role
- unreviewed
- Read
- now
arxiv
Score 12.2
2026-09-24 · Jiahong Liu, Ming Shen, Xiaohao Liu, Rex Ying, Menglin Yang, Tat-Seng Chua, Irwin King
Research Track A · General AI
Existing continual-learning methods protect parameters, replayed examples, or Euclidean feature subspaces. When applied to hyperbolic multimodal models, they do not explicitly preserve the Lorentz geometry that jointly encodes within-modality similarity, cross-modal correspondence, and semantic hierarchy; sequential up…
- Review
- pending
- Role
- unreviewed
- Read
- now
huggingface
Score 11.4
2026-09-24 · Shaohua Dong, Zexuan Meng, Haiyan Sun, Bing Fan, Cuicui Zhang, Dylan Joseph, Kewei Sha, Yunhe Feng, Heng Fan
General AI
In this paper, we propose RGBD20K, a novel dataset for facilitating the development of more robust and general RGB-D semantic segmentation by encompassing abundant categories and high-quality annotations. RGBD20K possesses several attractive properties: (1) Expanded Semantic Space. In particular, it covers 160 fine-gra…
- Review
- pending
- Role
- unreviewed
- Read
- now
arxiv
Score 11.2
2026-09-24 · Sriram Kannan, Swetha Saseendran, Vishnu Vardhan Reddy Kandi, Leslie Barrett, Madhavan Seshadri, Enrico Santus
General AI
U.S. employment-discrimination complaints describe complex event sequences that are not explicitly captured by lexical or embedding-based representations alone. We present ARGUS, a source-grounded pipeline that combines a 5W1H-inspired schema, legal-domain models, and LLM-based structured generation to construct docume…
- Review
- pending
- Role
- unreviewed
- Read
- now
arxiv
Score 11.2
2026-09-24 · Jiaxi Huang, Yueqi Hu, Xin Zhu, Xiaopeng Zhang, Huiting Qiao, Yanglin Zhang, Zefeng Ji, Rongxue Li, Yifei Xu, Huiying Yu, Wei Liu, Jiayin Zheng, Yinggan Xu, Peipeng Chen, Yin Zhang, Jian Yao
General AI
A generalist vision encoder must capture semantic, spatial, language-aligned, and action-relevant cues within a unified representation, yet softmax attention underlying today's most capable visual backbones becomes prohibitively expensive at high resolution. A natural attempt to address both challenges is to distill mu…
- Review
- pending
- Role
- unreviewed
- Read
- now
arxiv
Score 11.2
2026-09-24 · Mehmet Iscan
General AI
An acceptance protocol is developed for sensor-coordinate and polarity binding in mechatronic commissioning. Candidate generation is separated from release authority. Requirements unsupported by a deterministic parser are routed to a frozen local language model with four billion parameters. Plans are released only when…
- Review
- pending
- Role
- unreviewed
- Read
- now
arxiv
Score 11.2
2026-09-24 · Sudip Bhujel, Shanghao Shi, Ruiquan Huang, Ning Zhang, Yang Xiao
General AI
Distributed learning in embodied reinforcement-learning agents offers a degree of privacy by retaining raw sensor data on-device and transmitting only policy gradients to the server. Yet temporal structure can amplify this leakage beyond single-frame attacks. We introduce Temporal Reconstruction Attack on Consecutive E…
- Review
- pending
- Role
- unreviewed
- Read
- now
arxiv
Score 11.2
2026-09-24 · Hong-Han Wang, Yuntao Wang, Hu Ding
General AI
Layer-wise visual-text similarity in Multimodal Large Language Models (MLLMs) is widely interpreted as evidence that the language model progressively integrates visual content into a shared representation space. This reading rests on the assumption that scalar alignment scores reflect content-level cross-modal interact…
- Review
- pending
- Role
- unreviewed
- Read
- now
arxiv
Score 10.4
2026-09-23 · Romain Facq, Sami Ben Ali, Olivier Sentieys
Research Track A · General AI
Microscaling quantization techniques are increasingly used to represent neural network parameters with 8 bits or fewer while preserving near-full precision accuracy. However, applying these methods efficiently in convolutional layers is not straightforward. A naive approach transfers full-precision weights and activati…
- Review
- pending
- Role
- unreviewed
- Read
- soon
huggingface
Score 10.4
2026-09-24 · Chia-Yuan Chang, Renyuan Cheng, Rui Feng, Xiaotian Han, Yuan He, Hongye Jin, Linwei Li, Shiyang Li, Fenglin Liu, Xin Liu, Priyanka Nigam, Haoyang Wen, Zhenghao Xu, Zhuocheng Xu, Bing Yin, Qingyu Yin, Chao Zhang, Rongzhi Zhang, Zhihan Zhang, Zixuan Zhang, Tuo Zhao
General AI
Rufus-Air is an open and reproducible post-training recipe on GLM-4.5-Air-Base (106B-A12B), organized as a serial pipeline of eight stages: SFT, Reasoning RL, Coding RL, Instruction-Following RL, General Agent, Coding Agent, Search Agent, and RLHF. We document the data, reward design, infrastructure, stage order, and s…
- Review
- pending
- Role
- unreviewed
- Read
- soon
huggingface
Score 10.4
2026-09-24 · Zichong Meng, Chongjian Ge, Chun-Hao P. Huang, Yang Zhou, Huaizu Jiang
General AI
Few-step autoregressive (AR) video diffusion enables low-latency streaming generation, but existing post-training methods predominantly rely on Distribution Matching Distillation (DMD), requiring both a large pretrained teacher and an online critic to estimate distributional discrepancies through diffusion scores. In t…
- Review
- pending
- Role
- unreviewed
- Read
- soon
huggingface
Score 10.4
2026-09-24 · Yubo Zhu, Yawen Shao, Ziyun Dai, Zixun Fang, Kai Zhu, Siyang Sun, Haolan Xue, Chuxin Wang, Tingyu Weng, Jingming Luo, Chen Shi, Lianghua Huang, Yufeng Ai, Yuzheng Wang, Wenyuan Zhang, Yu Shang, Yuxiang Bao, Zoubin Bi, Jie Xiao, Jinbo Xing, Jiaxing Zhao, Chongyang Zhong, Hengjian Chen, Chenwei Xie, Akide Liu, Zhehan Kan, Yu Liu, Wei Zhai, Sheng Zhong, Wei Tong
General AI
Video generation begins in text space by authoring a cinematic screenplay, then materializes into pixels. As contemporary video generators scale to 30 seconds and faithfully follow complex conditions, the textual prompt largely directs the production, planning how actions, camera trajectories, lighting, and sound unfol…
- Review
- pending
- Role
- unreviewed
- Read
- soon
arxiv
Score 10.2
2026-09-24 · Yang Zhou, Jiuhong Xiao, Shizhao Ye, Long Quang, Carlos Nieto-Granda, Giuseppe Loianno
General AI
Robotic novel view synthesis (NVS) must recover both visual appearance and metric 3D structure, yet most generative NVS methods rely only on images, overlooking LiDAR, a complementary sensor common on robotic platforms. We present M3GD, a Camera--LiDAR multimodal representation for generative NVS that composes independ…
- Review
- pending
- Role
- unreviewed
- Read
- soon
arxiv
Score 10.2
2026-09-24 · Ruixin Zhang, Jiho Shin, Hung Viet Pham, Song Wang
General AI
Ensuring high structural coverage remains a fundamental challenge in automated test generation, particularly for complex software systems where reaching specific lines or branches requires satisfying intricate control- and data-flow constraints. Large Language Models (LLMs) have recently demonstrated strong capabilitie…
- Review
- pending
- Role
- unreviewed
- Read
- soon
arxiv
Score 10.2
2026-09-24 · Wenhao Li, Zhibin Wu, Chong Xiao, Qiangchang Wang
General AI
Recent research on Multimodal Sentiment Analysis (MSA) has focused on learning from language, visual, and acoustic modalities with incomplete data to infer human sentiment. Most studies typically compensate for missing information by reconstructing modality features or designing complicated fusion mechanisms. However, …
- Review
- pending
- Role
- unreviewed
- Read
- soon
arxiv
Score 9.9
2026-09-24 · Kidus Seyoum, Ajay Mittur
Research Track A · General AI
Agent behavior depends on the harness surrounding a language model, but it remains unclear whether language models can reliably improve such harnesses for hardware-design tasks. We study automatic harness evolution around a fixed subject model on 12 proprietary design-verification root-cause localization tasks. Across …
- Review
- pending
- Role
- unreviewed
- Read
- soon
arxiv
Score 9.4
2026-09-23 · Teeratham Vitchutripop, Alyssa Quarles, Wenhe Zhang, Richard Xue, Daniel Rakita
Research Track A · General AI
Over the course of a lifetime, robots may encounter novel scenarios unaccounted for in its original training that result in performance degradation. One common approach to mitigating this issue is to further grow the offline training dataset in hopes of producing a policy robust to these changes. In contrast, biologica…
- Review
- pending
- Role
- unreviewed
- Read
- soon
arxiv
Score 9.2
2026-09-24 · Yinghua Zhou, Junjie Ye, Yiqi Zhao, Hao Dong, Celina Shiyu Wang, Ruohai Ge, Tingyi Yang, Basile Van Hoorick, Gaurav Sukhatme, Vitor Guizilini, Yue Wang
General AI
World Action Models (WAMs) couple action generation with future visual prediction for robotic manipulation. However, completing the joint video-action denoising process at each replanning cycle incurs substantial latency, delaying action updates and limiting closed-loop responsiveness. We present Rolling-WAM, a formula…
- Review
- pending
- Role
- unreviewed
- Read
- soon
arxiv
Score 8.4
2026-09-24 · Zhiyang Zhou, Yingxin Shang, Zhou Wang, Hongwei Cai, Weixu Wang, Shuran Zhou, Shuofeng Zhao, Wenke Fan, Qingxiang Guo, Dawei Yang, Lin Yang, Yang Song
Research Track A · General AI
Full-duplex spoken dialogue requires simultaneous listening and speaking at sub-second latency, under conversational timing and cognitive demands that change moment to moment. Yet current models mostly impose static operating points, lacking a systematic mechanism for adaptive decisions. We present AdaptDuplex, which u…
- Review
- pending
- Role
- unreviewed
- Read
- soon
huggingface
Score 8.4
2026-09-24 · Ruoqi Guo, Yi Liu, Gelei Deng, Yuekang Li, Lida Zhao, Yutao Wu, Simin Chen, Ying Zhang, Leo Yu Zhang
General AI
Detectors of alignment failures screen deployed language models and score alignment benchmarks. Most are generative judges that spend a decoding pass on every criterion, and classifiers that read token probabilities, such as Llama Guard, still score one fixed label per call. Jev, a model trained with reinforcement lear…
- Review
- pending
- Role
- unreviewed
- Read
- soon
arxiv
Score 7.7
2026-09-24 · Leon Rode, Sumeet Khatri, Supartha Podder
General AI
Future quantum networks will make use of entanglement to perform numerous tasks, such as sending quantum information over long distances, distributed quantum computing, and quantum sensing. In general, these tasks will need to be performed simultaneously in various regions of a network, while minimizing resources and l…
- Review
- pending
- Role
- unreviewed
- Read
- soon
huggingface
Score 7.4
2026-09-23 · Han Yan, Zishang Xiang, Haokai Jiang, Zeyu Zhang, Qilin Wang, Weiyu Guo, Yandong Guo, Boxin Shi, Hao Tang
General AI
World-action models (WAMs) transfer visual and motion priors from pretrained video generators to robot control by jointly modeling visual dynamics and actions. Existing WAMs, however, predict dense future frames during training, repeatedly modeling largely unchanged content and coupling action-conditioned dynamics to n…
- Review
- pending
- Role
- unreviewed
- Read
- soon
huggingface
Score 7.4
2026-09-24 · Ming Zhang, Zhenghao Xiang, Peizhong Gao, Yujiong Shen, Yuhui Wang, Zhonghan Yue, Shihan Dou, Zhangyue Yin, Junjie Ye, Shichun Liu, Weihuang Zheng, Jiahao Chen, Jiayi Chen, Hongzhang Liu, Jiaqi Shao, Tao Gui, Qi Zhang, Xuanjing Huang, Suncong Zheng, Maxm Pan
General AI
Scientific discovery begins where known problems end. There, AI systems must engage in exploration: framing hypotheses, designing experiments, and iterating on the results. However, evaluating this ability is difficult: (1) how to verify whether a genuinely new hypothesis holds, and (2) how to determine whether a syste…
- Review
- pending
- Role
- unreviewed
- Read
- soon
arxiv
Score 7.2
2026-09-24 · Abhilasha Saroj, Pranav Govindu, Bharat Sharma, Usman Ahmed
General AI
State crash databases differ in structure, coding, and injury-severity distributions, limiting direct reuse of predictive workflows across jurisdictions. This study adapts the SafeTraffic Copilot large language model (LLM) crash-severity workflow to a three-year Tennessee inventory of 624,392 crashes. Tennessee crash, …
- Review
- pending
- Role
- unreviewed
- Read
- soon
arxiv
Score 7.2
2026-09-24 · Guoming Ling, Muen Xue, Zijian Ye
General AI
Jev is a fast, low-cost decision model that answers natural-language questions with choices, binary judgments, and scores. As its public ecosystem grows rapidly, it remains unclear how Jev is used across applications and how public attention relates to project distribution. To answer these questions, we conduct a large…
- Review
- pending
- Role
- unreviewed
- Read
- soon
arxiv
Score 7.2
2026-09-24 · Md Maklachur Rahman, Md Hasan Al Banna, Saraf Anjum, Assame Arnob, Tracy Hammond
General AI
Textual descriptions can reduce ambiguity in medical image segmentation by specifying the finding and location to be delineated. Existing text-guided methods mainly improve where image and language features interact but generally retain a single learned update pathway across all image-text pairs. We propose MRSeg, a pa…
- Review
- pending
- Role
- unreviewed
- Read
- soon
huggingface
Score 6.4
2026-09-23 · Niket Patel, Ahmad Rammal, Amaury Hayat, Remi Munos, Julia Kempe
General AI
Recently, Large Language Models (LLMs) have been increasingly able to solve advanced mathematical problems, including many that have been open for decades. This opens the door to expansion of mathematical knowledge at unprecedented scale. Yet, while LLMs may be able to conjecture and prove more and more theorems, it re…
- Review
- pending
- Role
- unreviewed
- Read
- later
huggingface
Score 6.4
2026-09-24 · Pavel Tikhonov, Anton Korznikov, Matvey Mikhalchuk, Nikita Dragunov, Temurbek Rahmatullaev, Polina Druzhinina, Anton Razzhigaev, Ivan Oseledets, Elena Tutubalina
General AI
While Large Language Models (LLMs) rely on highly non-linear components, in this work we demonstrate that they exhibit fundamental linearity: when inputs from distinct text streams are linearly combined, the model outputs a superposition of the individual next-token distributions. We term this the Superposition Lineari…
- Review
- pending
- Role
- unreviewed
- Read
- later
arxiv
Score 6.2
2026-09-23 · Hannan Cao, Jun Guo, Haolei Pei, Zhaoqi Zhang, Tianyu Wang, Ziyang Wang, Youchen Sun, Yue Xue, Yucheng Mao, Lintao Yan, Yufei Feng, Shaowei Liu, Rongkun Xing, Feiling Gong, Xinyu Chenli, Cong Xu, Mingge Zhang, Yunjia Zhu, Yajing Zhang, Pengfei Ren, Yue Lin
General AI
Industrial recommendation systems typically operate as a \emph{cascade} of retrieval, pre-rank, and fine-rank, but these stages are usually trained and served as separate models, causing repeated user-sequence encoding, isolated optimization, and duplicated engineering effort. Building on OneTrans' model-level unificat…
- Review
- pending
- Role
- unreviewed
- Read
- later
arxiv
Score 6.2
2026-09-24 · Jiabin Qiu, Zixuan Chen, Hongye Cao, Jieqi Shi, Jing Huo, Yang Gao
General AI
Latent world models are typically trained to predict factual transitions, whereas model predictive control (MPC) must compare alternative actions from the same state. A model can therefore achieve low factual prediction error yet poorly distinguish candidate actions. We introduce AD-WM, an action-discriminative joint-e…
- Review
- pending
- Role
- unreviewed
- Read
- later
arxiv
Score 6.2
2026-09-24 · Zebang Xie, Chuanyang Zheng, Yik-Chung Wu, Yihang Gao
General AI
Low-rank adaptation (LoRA) has become a popular parameter-efficient fine-tuning method for large language models. A key challenge in LoRA is how to determine the rank of each adaptation matrix, as rank directly controls its capacity and efficiency. Existing adaptive-rank methods typically allocate ranks according to ma…
- Review
- pending
- Role
- unreviewed
- Read
- later
arxiv
Score 6.2
2026-09-24 · Ben Liang, Chao Sui, Junqi Bai, Yuan Liu, Chunlai Li, Xiubao Sui, Qian Chen
General AI
In aerial RGB--IR object detection, effectively exploiting complementary information across modalities is critical for robust perception under complex illumination and environmental conditions. Existing multimodal detectors mainly focus on spatial-domain interaction or frequency-specific feature enhancement, while the …
- Review
- pending
- Role
- unreviewed
- Read
- later
arxiv
Score 6.2
2026-09-24 · Jeremy Qin, David Schmotz, Derck Prinzhorn, Luca Beurer-Kellner, Ameya Prabhu, Maksym Andriushchenko
General AI
Asynchronous monitoring, incident investigations, and compliance audits primarily rely on agent traces to reconstruct what happened. These analyses assume that LLM agents cannot tamper with their own execution traces. We show that local LLM agents such as Claude Code, Codex, Antigravity, Open Code and Grok Build fail t…
- Review
- pending
- Role
- unreviewed
- Read
- later
arxiv
Score 6.2
2026-09-24 · Se Un Park, Hakjun Kim, Taehoon Roh, Junyoung Park
General AI
We present a personalized Korean visual speech recognition (VSR) system and quantify, on the nine-camera OLKAVS corpus, the gap between the population-level benchmark score and an individual user's error. A video-only Conformer initialized from English-trained weights attains 9.95 - 12.19% character error rate (CER) un…
- Review
- pending
- Role
- unreviewed
- Read
- later
huggingface
Score 6.0
2026-09-19 · Chenyu Zhu, Ruoyu Zhao, Zhichao Lu
General AI
Modern Transformer design and compression both reduce to allocating capacity under a budget. The standard scalars for these decisions, #Params and #FLOPs, capture size and compute but not architectural structure: two architectures with identical parameter budgets but different depth-width, head, or FFN allocations rece…
- Review
- pending
- Role
- unreviewed
- Read
- later