AgriJev is a family of adapted Qwen3.5 models (0.8B, 2B, 4B, and 9B) designed for efficient agricultural candidate scoring. The models use a shared interface that conditions on agricultural text, a judgment question, and candidate definitions to return scores and relative probabilities in a single forward pass. Across 17 external test views, AgriJev-9B achieves 75.44% mean accuracy, surpassing both the original Qwen3.5 and matched agricultural SFT models, while also offering roughly half the median scoring latency of equivalent answer‑generation models on an A100 GPU.
By Xuechen Li (University of Minnesota Twin Cities)
The paper discusses the rapid progress of machine unlearning for multimodal large language models (MLLMs) and the need for rigorous evaluation. It identifies three pitfalls in current benchmarks: lack of held‑out evaluation, reliance on synthetic fine‑tuned knowledge, and unfair comparisons across methods. To address these issues, the authors propose GEMMU, a benchmark using real‑world knowledge and a principled protocol, and show that re‑evaluating existing methods under GEMMU uncovers significant generalization gaps.
By Oscar Chew, Po-Yi Lu, Yi-Jie Cheng, Kunal Jain, Hsuan-Tien Lin, Zhengzhong Tu, Kuan-Hao Huang
Interlock is a framework that transforms long‑horizon tasks into typed completion graphs, linking evidence, decisions, and required effects through grounding, coupling, and realization edges. It compiles these graphs into a resettable workspace, a public request, and an evaluation rubric, and uses source‑coverage, public‑input, and agent‑as‑judge reviews to ensure that all mandatory requirements are met. Fine‑tuning Qwen3.6 backbones on Interlock‑generated trajectories improves pass rates on AutomationBench, JobBench, and Harvey LAB, showing that the synthesized experience benefits external task environments.
By Linji Hao, Yanji He, Zihan Wang, Hansi Yang, Jiayuan Zhang, Hongyan Hao, Qi Gu, Yan Feng, Han Wu
Qwen-MT-Lumen is an open‑source translation model submitted to the WMT 2026 General Machine Translation Shared Task. It employs a four‑stage pipeline that combines continued pre‑training, supervised fine‑tuning, online preference‑optimization with an LLM judge, and on‑policy distillation from a larger teacher to a Qwen3‑14B student. The system also uses structure‑aware inference and selective repair to preserve formatting and correct decoding errors, achieving an overall mean score of 4.60 on a 1–5 rubric and matching leading proprietary systems in both translation quality and instruction adherence.
By Hao Wang, Yangyang Liu, Xiaohu Zhao, Heng Liu, Zifu Shang, Tianhao Li, Ruize Gao, Jialong Tang, Liangying Shao, Haoran Wei, Baosong Yang, Linlong Xu, Longyue Wang, Weihua Luo
The paper introduces Length‑Conditioned Majority Voting (LCMV), a test‑time training method that enhances the standard Majority Voting (MV) technique for Large Language Models (LLMs). LCMV incorporates an empirical bias that longer Chain‑of‑Thoughts (CoTs) are less likely to be correct by modeling a length‑conditioned prior with a logistic function. This prior is adapted on unlabeled test data without fine‑tuning the LLM, and the resulting weighted votes consistently outperform standard MV and other length‑ or confidence‑based aggregation strategies across multiple reasoning benchmarks.
By Fiorenzo Parascandolo, Enver Sangineto, Xiaoyi Yu, Wenhui Tan, Jipei He, Ruihua Song, Rita Cucchiara
The paper introduces a two‑stage method for uncovering hidden concepts encoded in Low‑Rank Adaptation (LoRA) adapters used to personalize diffusion models. First, Subspace‑Guided Evolutionary Search (SGES) identifies promising prompts by evaluating their alignment with the LoRA subspace without rendering images. Second, Paired Visual Identification (PVI) renders only the shortlisted prompts and compares LoRA outputs to the base model to confirm coherent, distinctive generation, thereby efficiently revealing undisclosed concepts.
By Yupeng Qiu, Han Fang, Dhananjai Sharma, Ee-Chien Chang
The study investigates how language models acquire in-context learning (ICL) by distinguishing between copying a nearby demonstration and integrating information across a prompt. Across 17 models, roughly one-third default to copied answers, a few are undecided, and the remainder favor rule-consistent answers that yield higher accuracy and are guided by the requested value rather than the nearest conflicting example. Analyses show that models prioritize task-relevant prompt tokens before accuracy surpasses chance, and that synthetic or fine-tuned training can shift models toward compositional responses or improve accuracy when prompts reassign label meanings.
By Minglai Yang, Xinyu Guo, Renxiong Wang, Sunjie Hou, Daniel Yue Zhang, Yunzhong He
arXiv:2610.20474v1 Announce Type: new
Abstract: Pretrained vision-language-action models (VLAs) often fail midway through unseen long-horizon tasks. Recursive self-improvement (RSI) offers a remedy,...
By Peidong Wang, Ying Chang, Zhiming Ma, Xiaocui Yang, Shi Feng, Daqi Liu, Yuzhe Yang, Xu Cao, Chuang Wang, Jian Su, Daling Wang
arXiv:2610.19108v1 Announce Type: cross
Abstract: Multimodal Large Language Models (MLLMs) have been widely applied in embodied agents and robotics for vision tasks. However, MLLMs suffer from limita...
By Mahdieh Mallahnezhad, Masoud Jafaripour, Mohamadali Tofigh, Sheila Schoepp, Osmar R. Zaiane
arXiv:2510.13928v3 Announce Type: replace
Abstract: We propose and test the LLM Brain Rot Hypothesis: continual exposure to junk web text induces lasting cognitive decline in large language models (L...
By Shuo Xing, Junyuan Hong, Yifan Wang, Runjin Chen, Zhenyu Zhang, Ananth Grama, Zhengzhong Tu, Zhangyang Wang
arXiv:2604.03925v2 Announce Type: replace
Abstract: Large language models (LLMs) struggle to accumulate evidence across multiple rounds of user interactions, failing to update their beliefs in a mann...
By Fangzhou Lin, Zilin Dai, Shuo Xing, Peiran Li, Siyuan Yang, Qianwen Ge, Kazunori Yamada, Yang Zhou, Ziming Zhang, Haichong Zhang, Zhengzhong Tu
arXiv:2610.19266v1 Announce Type: new
Abstract: Existing illumination estimation methods primarily recover lighting distributions for rendering, but typically leave the contributions of individual ph...
By Yanqiao Wang, Jin Sun
arXiv:2610.20083v1 Announce Type: new
Abstract: Visual world knowledge is a core capability of multimodal large language models (MLLMs), underpinning knowledge-intensive visual question answering and...
By Chen Chen, Zheming Liang, Jiaqi Wang
arXiv:2610.20584v1 Announce Type: new
Abstract: Computer-use agents have demonstrated strong capabilities in interpreting screens and executing keyboard and mouse actions. However, games, with their...
By Mingyu Ouyang, Yiran Wang, Siyuan Hu, Xingyilang Yin, Huiqiang Sun, Guangzhi Wang, Junfu Pu, Cheng Cheng, Honghao Chen, Ying Shan, Mike Zheng Shou, Hwee Tou Ng
arXiv:2412.12048v2 Announce Type: replace
Abstract: Low-Rank Adaptation (LoRA) has become a standard approach for parameter-efficient fine-tuning of image diffusion models, with over 200K models trai...
By Chenxi Liu, Towaki Takikawa, Alec Jacobson
arXiv:2512.01495v4 Announce Type: replace
Abstract: Video instance segmentation (VIS) for low-light content remains highly challenging for both humans and machines alike, due to noise, blur and other...
By Joanne Lin, Ruirui Lin, Yini Li, David Bull, Nantheera Anantrasirichai
arXiv:2610.18038v2 Announce Type: replace-cross
Abstract: World action models (WAMs) built on pretrained video generation models adapt quickly to new robotic tasks, but they forget previously learned...
By Kaipeng Fang, Hangxu Liu, Chaojian Shi, Yunsong Zhou, Hongzi Zhu, Minyi Guo, Jingkuan Song, Lianli Gao
The paper investigates how large language model (LLM) workflows and agents make binary decisions—such as allowing or blocking an input—when human deferral is not possible. It proposes using System One decision scores that default to a conservative fallback in uncertain cases and control false omission risk within the subset of inputs that receive the utility‑maximizing action. Experiments on six datasets spanning moderation, safety, and reranking show that naive threshold baselines often exceed target risk, whereas a Learn‑Then‑Test approach achieves only 7.8% risk, demonstrating the limitations of probability‑like interfaces and the benefits of risk‑budgeted selection.
By Soundouss Messoudi, Youness Mansar
The paper presents a method for adapting a single vision‑language model, Qwen3.5‑9B, to medical image parsing tasks by using task‑specific low‑rank adapters (LoRA) selected from the input question. The system employs a frozen 4‑bit backbone and customizes adapter ranks, prompts, and class rebalancing across six task families and seven imaging modalities, achieving strong performance on the FLARE 2026 Task 3 dataset and a hidden‑validation set. The authors provide code and demonstrate that task‑specific adapter configurations and image budgets improve performance across diverse medical imaging tasks.
By Taha Sabir, Alberto Montero Molina, Thinh Quang Ly, Veronika Dmitrenko, Mohammad Yaqub, Tausifa Jan Saleem
The paper introduces HiRe-MoMa, a hierarchical residual policy learning framework that fine‑tunes a frozen base policy for mobile manipulation. It uses a policy‑agnostic residual split into mobile‑base and manipulator‑arm heads to reduce gradient interference, and incorporates expert‑guided value alignment to improve sample efficiency with sparse human interventions. Experiments on the TIAGo++ platform show that HiRe‑MoMa boosts task performance after only about 30 minutes of online interaction, regardless of the underlying base policy.
By Zhefei Gong, Hefeifei Jiang, Zehao Wang, Jiachen Li