Spectral Feedback is a new algorithm for aligning discrete diffusion models at test time by iteratively revisiting and editing token positions rather than only steering the reverse process. It selects edit-sets—groups of token positions to re-mask and re-sample—using sparse Fourier representations of edit-set value functions, enabling efficient optimization of which tokens to revisit. The method is model-agnostic and improves alignment performance across pretrained, test‑time aligned, and fine‑tuned diffusion models, achieving significant gains in protein stability for inverse folding tasks.
By Shai Dickman, Mert Cemri, Landon Butler, Kannan Ramchandran
FeatMark is a watermarking framework that protects images from text‑to‑image diffusion model mimicry attacks by embedding small, scene‑consistent micro‑features instead of pixel‑level perturbations. It constructs domain‑specific feature banks, selects executable features, and injects them via mask‑guided concept editing to create highly localized, natural edits. Experiments on VGGFace2, CelebA‑HQ, and WikiArt show FeatMark remains robust against ten strong watermark removal attacks and several adaptive attacks, with minimal impact on perceptual quality and extending to video mimicry scenarios.
By Haoyang Li, Ruoxi Sun, Qingqing Ye, Benjamin Zi Hao Zhao, Yaxin Xiao, Jason Xue, Haibo Hu
The paper introduces PORL, a hybrid method that first trains a general scheduling policy through online reinforcement learning in simulation, then fine‑tunes it offline on production data using a KL‑divergence constraint to limit policy drift. PORL is evaluated on Job Shop Scheduling Problem instances with distribution shifts and various data sources, consistently outperforming standalone offline RL and other baselines, especially when offline data quality is low. The results suggest that offline adaptation of pretrained policies can improve industrial scheduling when direct online exploration is impractical.
By Mateo Toro Diz, Jonathan Hoss, Noah Klarmann
arXiv:2609.31193v1 Announce Type: new
Abstract: Current Audio-Visual LLMs (AVLLMs) struggle with reasoning over videos featuring multi-speaker dialogues. In such videos, resolving "who says what" is...
By Jihoo Jung, Youngjoon Jang, Joon Son Chung
The paper demonstrates that fine‑tuning reasoning models to predict their own confidence at intermediate steps—using only 600 self‑supervised examples—substantially improves inference efficiency. Without adding any explicit stopping or length penalties, the models generate up to 25 % fewer tokens while maintaining accuracy on mathematical, scientific, and coding benchmarks across several architectures. The study finds that confidence supervision preserves the models’ high‑level reasoning structure rather than merely suppressing specific behaviors.
By Parsa Hosseini, Akasha Tigalappanavara, Sumit Nawathe, Chenrui Fan, Sourya Basu, Genta Indra Winata, Anirban Das, Soheil Feizi, Nima Chitsazan
DeepEdu‑v1 is an AI‑tutoring system tailored for Vietnamese education that addresses data‑sovereignty and local curriculum alignment issues. It uses a long‑context inference engine to reduce retrieval calls and prefill latency by about 35%, and a self‑improving agentic layer that curates verified local knowledge without fine‑tuning. In deployment, DeepEdu achieves nearly twice the speed of standard vLLM serving and raises agentic accuracy from 70.0% to 79.5% on complex tasks, especially in financial reasoning and interactive‑agent benchmarks.
By Quang Nguyen, Hieu Nguyen, Hien Hoang, Toan Pham, Cong Tran, Nam Vu
arXiv:2609.31461v1 Announce Type: new
Abstract: Background: Large volumes of unlabeled knee MRI scans are available across repositories but remain insufficiently leveraged. We developed KneePreM, a k...
By Xinxin Wang, Liam Hazan, Jing Li, Simona Rabinovici-Cohen, Xiaojuan Li, Mingrui Yang
The paper introduces Cross-Scale Channel-wise Knowledge Distillation (CSCWD), a training-time framework that transfers high‑resolution spatial representations from a YOLO11m‑P2 teacher to a lightweight YOLO11n student without changing the student’s inference architecture. CSCWD aligns teacher P2 features with student P3 while also applying same‑scale distillation at deeper pyramid levels, yielding a 2.92‑point mAP@0.5 improvement over the baseline and a 2.09‑point gain over same‑scale distillation alone. In zero‑shot tests on DUT‑Anti‑UAV and on a Raspberry Pi 5, the 2.58‑million‑parameter student reaches 50.32% mAP@0.5 at 82.32 ms latency (12.15 fps) with negligible runtime or memory increase.
By Amir Zamani, Zeinab Ghasemi-Naraghi
The study investigates how prompt template choices during Knowledge Distillation (KD) affect safety alignment in language models. It finds that using chat templates during KD degrades safety alignment, making models more compliant with harmful queries, while non-chat templates better preserve the base model’s internal representations. These effects are observed across LLaMA, Gemma, and Qwen families on multiple safety benchmarks.
By Anjila Budathoki, Manish Dhakal, Benjamin M. Ampel, Yi Ding
The paper introduces Human-1, the first open and reproducible full‑duplex spoken dialogue system for Hindi. It adapts the Moshi architecture with a custom Hindi tokenizer and trains on 26,000 hours of real spontaneous conversations from 14,695 speakers, enabling the model to learn natural turn‑taking, interruptions, overlaps, and backchannels. A two‑stage training process—large‑scale pre‑training followed by fine‑tuning on 1,000 hours—yields a system that, according to both automatic metrics and human judgments, generates natural and meaningful full‑duplex conversational behavior in Hindi.
By Bhaskar Singh, Manas Dhir, Shobhit Banga, Pranav Sharma
Neural State Prediction (NSP) is a latent‑predictive framework designed to curb shortcut learning in EEG foundation models. By using a target encoder updated with an exponential moving average, identity residualization, and topology‑separated context, NSP constrains both the prediction target and the available context. Trained on 2.2 million EEG segments, NSP outperforms baselines on 14 datasets in the EEG‑FM‑Bench, achieving 63.94 % macro balanced accuracy.
By Kieren Yu, Ziyang Liu, Chang Huang, Jintai Chen, Kaishun Wu
DepthEvidence is a 4B multimodal language model that integrates dense metric depth predictions into language generation. It employs a camera‑conditioned decoder to produce full‑resolution depth maps and a dense‑to‑language interface that converts these predictions into object‑aligned geometry tokens. The model is trained with geometric supervision and instruction tuning, and it sets new state‑of‑the‑art results on a Depth‑VQA benchmark and on instance‑level metric depth estimation across nine datasets.
By Jiangning Wei, Yuan Yao, Miaomiao Cui, Mingsheng Li, Humen Zhong, Shuai Bai, Zhibo Yang
arXiv:2609.31356v1 Announce Type: new
Abstract: Vision-Language Models (VLMs) exhibit remarkable zero-shot generalization, yet they often encode unwanted or hazardous stylistic domains such as ideali...
By Sumanth Udupa, Mehrtash Harandi, Yadan Luo, Mahsa Baktashmotlagh
arXiv:2503.10685v3 Announce Type: replace
Abstract: Unsupervised Domain Adaptation (UDA) enables strong generalization from a labeled source domain to an unlabeled target domain, often with limited d...
By Brun\'o B. Englert, Gijs Dubbelman
arXiv:2504.18190v2 Announce Type: replace
Abstract: Unsupervised Domain Adaptation (UDA) can improve a perception model's generalization to an unlabeled target domain starting from a labeled source d...
By Brun\'o B. Englert, Tommie Kerssies, Gijs Dubbelman
Agentick is a unified benchmark for sequential decision‑making agents that evaluates RL, LLM, VLM, hybrid, and human agents on 37 procedurally generated tasks across six capability categories, four difficulty levels, and five observation modalities via a single Gymnasium‑compatible interface. It includes a Coding API, oracle reference policies, pre‑built SFT datasets, a composable agent harness, and a live leaderboard. An evaluation of 27 configurations and over 90,000 episodes shows no single approach dominates, with GPT‑5 mini leading overall, PPO excelling in planning and multi‑agent tasks, and the reasoning harness boosting LLM performance by 3‑10×, while ASCII observations outperform natural language.
By Roger Creus Castanyer, Pablo Samuel Castro, Glen Berseth
JevSoup is a training‑free framework that separates System One expert routing from System Two execution for low‑rank adaptation (LoRA) models. It selects two experts based solely on input and expert descriptions, retains the leading expert’s update, projects the second onto the orthogonal complement of the first update’s row space, and combines them with equal weights. On 14 PorTAL tasks and three Qwen3 scales, JevSoup improves task‑macro accuracy by up to 1.19 % and sample‑micro accuracy by up to 1.21 % over the strongest evaluated baselines.
By Xiuying Wang, Jiahua Cheng, Shuotian Li, Yufan Cheng, Bowen Deng, Zhexuan Bai, Yichen Li
The paper introduces FTB Graph, a method for mapping the causal circuitry that determines the first-token language identity in multilingual language models. Using Edge Attribution Patching and exact activation patching across six architectures (GPT‑2, BLOOM‑560M, Pythia‑1B/2.8B, Qwen2.5‑1.5B Base/Instruct), the authors extract directed acyclic graphs that reveal deep or mid‑to‑deep broadcasting hubs, with notable differences among models. The study finds that first‑token routing is largely established during pretraining and largely preserved by instruction tuning, while linear gradient approximations can diverge from causal interventions, underscoring the need for exact‑patching verification.
By Arjun Pillai, Christian Hoang, Anjelo Laroza
The paper investigates why retrieval‑based open‑ended evaluation fails in medical fact verification. By creating two detailed taxonomies—one for retrieval‑stage errors across five quality dimensions and another for verifier‑reasoning errors across six steps—the authors automatically label evidence quality and reasoning errors using an LLM‑as‑Judge pipeline. Their large‑scale stress tests across multiple retrieval methods and verifier models show that increasing model size, reasoning effort, source breadth, or medical fine‑tuning does not eliminate these failure modes, indicating fundamental limits of the retrieve‑then‑verify paradigm in open‑ended medical contexts.
By Heyuan Huang, Jirui Dai, Alexandra DeLucia, Sonal Joshi, Mahsa Yarmohammadi, Jie Gao, Bernal Jim\'enez Guti\'errez, Mark Dredze
The paper introduces CodeHack, a library of code-based skills with natural-language descriptions designed to improve language agents in complex environments like NetHack. By allowing agents to invoke reusable skills instead of selecting individual actions, the study shows that skill-based agents nearly triple game progression and cut inference cost by 86% in zero‑shot settings, while still retaining the option to fall back on primitive actions. In reinforcement learning, skill-based agents learn faster, achieving a 7.2× larger average gain in dungeon level within the same training budget.
By Bart{\l}omiej Cupia{\l}, Jens Tuyls, Maciej Wo{\l}czyk, Davide Paglieri, Martin Klissarov, Benjamin Eysenbach, Piotr Mi{\l}o\'s, Karthik R. Narasimhan