The technical report introduces Gander, an end‑to‑end model that integrates omni perception, real‑time interaction, and agentic capabilities into a single framework. Unlike traditional turn‑based systems, Gander continuously processes streaming inputs from video, speech, and text, enabling natural full‑duplex interaction in both everyday conversations and workflow‑oriented scenarios. Its architecture features a Cerebellum‑Brain collaboration—where the Cerebellum handles real‑time interaction and omni conversational tasks while the Brain manages complex reasoning—and a streaming Thinker‑Talker design that flattens inputs and outputs into an ordered token stream for low‑latency, continuous dialogue. Evaluations across conversational ability, omni understanding, interactive capability, and agentic intelligence show that Gander matches state‑of‑the‑art open‑source models in spoken dialogue while maintaining robust performance in noisy, multi‑party, and backchannel environments.
By Orantqing, Shengpeng Ji, Junlong Tong, Jialong Zuo, Dongjie Fu, Di Cao, Yangzhuo Li, Shangda Wu, Franz, Evan, Theron Veyra, Changhao Pan, Jingyu Lu, Dongchao Yang, Zhifei Xie, Yang Tan, Xiaoyu Shen, Xiaoda Yang, Wenfu Wang, Teddy Sun, Steve Yves, Zhou Zhao
arXiv:2609.09158v1 Announce Type: cross
Abstract: We study the problem of navigating cluttered indoor environments with a humanoid robot. Unlike conventional methods that model navigation as a 2D pat...
By Anqi Li, Yuxin Chen, Zhaobo Li, Zhuo Cao, Junli Ren, Masayoshi Tomizuka, Dhruv Shah
arXiv:2603.04949v2 Announce Type: replace
Abstract: As web agents close the gap with humans on benchmarks, one question arises: Do today's agents perform just as well on tomorrow's web? We introduce...
By Md Farhan Ishmam, Kenneth Marino
arXiv:2609.06079v1 Announce Type: new
Abstract: Vision-Language-Action (VLA) policies leverage pretrained vision-language models (VLMs) to guide action generation for robot control. VLMs provide hier...
By Zheng Lu, Haoran Liao, Wanqi Zhong, Yunhe Ni, Lijie Wang, Xingjie Fan, Zhisheng Chen, Yantang Qu, Meijia Chen, Tianyu Xin, Zirui Song, Yiming Li
The paper investigates whether automatic safety judges evaluate the content of a model’s reply or merely its style. By keeping the reply content fixed and adding various style wrappers—such as educational disclaimers, fake reasoning blocks, or token refusals—the authors show that many judges flip their verdicts, indicating that style can influence safety judgments. The study evaluates over 600 jailbreak examples across multiple judges, revealing that some judges are highly susceptible to style-based manipulation while others remain robust.
By Yongxi Zhou, Wenbo Ye, Yuanzhe Liu, Zihan Dong, Junwei Yao
arXiv:2609.10187v1 Announce Type: new
Abstract: In this work, we introduce language-aligned motion representations for domain-generalizable UPDRS-Gait severity estimation, aiming to learn semanticall...
By Soojie Kim, Muhammad Munsif, Minkyung Kim, Seungryul Baek
arXiv:2609.08869v1 Announce Type: cross
Abstract: Analysts in emerging equity markets keep answering the same questions. Did fundamentals match the market's response? How does the local currency co-m...
By Furqan Nasir, Muhammad Atif Saeed, Muhammad Ehsan, Sher Jeel Ahmad, Abdul Moiz Altaf
arXiv:2609.09889v1 Announce Type: new
Abstract: Automatic Speech Recognition (ASR) technology is fundamental to customer service automation and large-scale transcription. However, even advanced ASR m...
By Yonghyun Jun, Jimin Lee, Hwan Chang, Dongho Shin, Seolah Kim, Hwanhee Lee
arXiv:2605.28703v2 Announce Type: replace-cross
Abstract: Baldwinian and Lamarckian evolution have existed for a long time in evolutionary algorithms (EAs) without ever dominating the academic litera...
By In\`es Benito, Johannes F. Lutzeyer, Benjamin Doerr
arXiv:2609.04239v2 Announce Type: replace
Abstract: This technical report presents EXAONE Forecast for Finance (EXAONE Finance), a financial time series foundation model (TSFM) tailored to financial...
By Seunghan Lee, Jaehoon Lee, Jun Seo, Tae Yoon Lim, Dongwan Kang, Hwanil Choi, Minjae Kim, Sungdong Yoo, Junhyeok Kang, Sangjun Han, Soonyoung Lee, Wonbin Ahn
arXiv:2507.15393v2 Announce Type: replace-cross
Abstract: Phishing email is a critical step in the cybercrime kill chain due to the high reachability of victims' email accounts and the low cost of la...
By Ruofan Liu, Yun Lin, Yuxin Wang, Xiwen Teoh, Zhenkai Liang, Gongshen Liu, Haojin Zhu, Jin Song Dong
arXiv:2509.23552v2 Announce Type: replace-cross
Abstract: Antimicrobial Resistance (AMR) is a rapidly escalating global health crisis. While genomic sequencing enables rapid prediction of resistance...
By Md. Saiful Bari Siddiqui, Nowshin Tarannum
arXiv:2609.05576v1 Announce Type: new
Abstract: The paradigm of LLMs has rapidly shifted from passive language interfaces to autonomous Claw-like agents that execute long-horizon tasks across statefu...
By Yirong Zeng, Shen You, Jinhang Feng, Yufei Liu, Xiao Ding, Yutai Hou, Hao Cong, Yuxian Wang, Wu Ning, Wang Xu, Bibo Cai
arXiv:2604.16625v2 Announce Type: replace-cross
Abstract: Recent large language model (LLM) agents have shown promise in using execution feedback for test-time adaptation. However, robust self-improv...
By Weihua Du, Jingming Zhuo, Yixin Dong, Andre Wang He, Weiwei Sun, Zeyu Zheng, Manupa Karunaratne, Ivan Fox, Tim Dettmers, Tianqi Chen, Yiming Yang, Sean Welleck
arXiv:2609.06835v1 Announce Type: cross
Abstract: Agentic AI systems execute complex tasks through long-horizon workflows of planning, tool use, and multi-agent coordination. Task failures in these s...
By Chaoyu Zhang, Hexuan Yu, Heng Jin, Shanghao Shi, Ning Zhang, Yi Shi, Yulia R. Gel, Y. Thomas Hou, Wenjing Lou
arXiv:2609.10022v1 Announce Type: cross
Abstract: Modern TTS systems approach human quality for high-resource languages but degrade when clean speech data is scarce. Modern Greek exemplifies this, la...
By Georgios Syllas, Efthymios Georgiou, Kosmas Kritsis, Alexandros Potamianos
arXiv:2609.06882v1 Announce Type: cross
Abstract: Diffusion policies offer a powerful and expressive parameterization for continuous control. Yet, their integration with reinforcement learning remain...
By Mahmoud Selim, Cristina Cipriani, Karl H. Johansson
FastE is a training‑free, plug‑and‑play method that compresses token prefixes in large language model (LLM) embedding inference. It uses a shared fixed threshold on batch‑mean readout‑prefix alignment to decide when to compress and ranks prefix states by readout attention scores to keep the most important ones. Experiments on Qwen3‑Embedding models show that FastE can cut decoder‑backbone FLOPs by over 40% while preserving more than 99% of the original ranking quality across multiple benchmarks and tasks.
By Jinsong Shu, Jinyong Wen, Baokun Wang, Zhongle Xie, Lidan Shou, Weiqiang Wang, Gang Chen
DGCPath is a Distribution‑Aware Generative Contrastive framework designed for self‑supervised path representation learning. It combines a diffusion‑based view generator, a variational contrastive mechanism that aligns latent features at the distribution level, and a generative cross‑supervision module for view‑level consistency. Experiments on three real‑world trajectory datasets show that DGCPath surpasses state‑of‑the‑art baselines on two downstream tasks, indicating stronger generalization and representation effectiveness.
By Sean Bin Yang, Hao Miao, Zongyi Xu, Jilin Hu, Xiangmeng Wang, Hua Lu, Bin Yang, Christian S. Jensen
The paper reports the first Turing test for speech‑to‑speech systems, gathering 2,968 human judgments on conversations between nine state‑of‑the‑art S2S systems and 28 humans. None of the evaluated systems passed the test, highlighting a clear gap in human‑likeness. The authors diagnose the failure with an 18‑dimension taxonomy, finding that paralinguistic cues, emotional expressivity, and conversational persona—not semantic understanding—are the main bottlenecks, and they propose an interpretable model for automatic human‑vs‑machine discrimination.
By Xiang Li, Jiabao Gao, Sipei Lin, Xuan Zhou, Chi Zhang, Bo Cheng, Jiale Han, Benyou Wang