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
SLMFix is a code‑generation pipeline that uses a small language model fine‑tuned with reinforcement learning to correct syntactic errors in programs produced by large language models for domain‑specific languages. The approach relies on interpreter feedback to guide the error‑fixing process. Experiments show that SLMFix improves validator pass rates by 40% on low‑resource programming languages and removes over 50% of syntactic errors on high‑resource DSLs, outperforming supervised fine‑tuning even for 7B models.
By David Jiahao Fu, Aryan Gupta, Aaron Councilman, Yu-Xiong Wang, Vikram Adve
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
MACBT is a clinician‑facing AI decision‑support system that models the five‑stage CBT workflow with five collaborative agents and incorporates a CBT‑specific longitudinal memory module (CD Memory) to track cognitive distortions across sessions. The system generates pre‑session pathology reports and prioritises interventions, and was trained on a Chinese CBT dialogue corpus using a Qwen3‑14B backbone with supervised fine‑tuning and preference optimisation. Evaluation by GPT‑4 judges shows MACBT outperforms several existing chatbots in professionalism and clinical authenticity, and the memory‑augmented version improves session quality by 12.6% and achieves a longitudinal mean of 2.29 on continuity, progression, and personalization.
By De Jiang, Shuo Zhang, Weiwei Liao, Jianying Zhang, Chuanhui Yu, Hongen Liao, Kehong Yuan
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
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 presents a method for automatically distinguishing scientists from non‑scientists on X/Twitter using user biographies and tweets. It reports classification performance up to an F1 score of 0.88 with Random Forests and 0.96 with a contrastively fine‑tuned DeBERTa model in an ensemble. Additionally, the authors release two labeled datasets of X users and their content for further research.
By Philipp Meier, Katarina Boland, Laura Kallmeyer, Stefan Dietze
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 paper introduces TokenAdapt, a model‑agnostic tokenizer transplantation method that uses a hybrid heuristic to initialize new token embeddings, and a novel pre‑tokenization learning approach for multi‑word Supertokens to improve compression. TokenAdapt combines local subword decomposition and global semantic similarity to preserve semantics while reducing retraining needs. Empirical results show that TokenAdapt outperforms existing baselines such as Transtokenizer and ReTok, achieving lower perplexity ratios and significant compression gains.
By Shaurya Sharthak, Vinayak Pahalwan, Adithya Kamath, Adarsh Shirawalmath
arXiv:2609.31234v1 Announce Type: new
Abstract: Problem. Ultra-high-resolution (UHR) remote sensing with vague user intents has two bottlenecks: visual tokens are expensive, and tool calling must be...
By Zhongyu Pang
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
The paper introduces FAVoR, a method for federated personalized generation that mitigates author‑style homogenization caused by standard aggregation in parameter‑efficient fine‑tuning. Using the BlogText benchmark and ASCE diagnostics, the authors show that common federated PEFT baselines preserve semantic utility but blur author‑specific style. FAVoR employs a shared‑private adapter design, where clients upload shared updates while keeping author‑specific residual corrections locally, leading to improved style retention with minimal utility loss.
By Lu Han, Jingyao Zhang, Katy Ilonka Gero, Nguyen H. Tran
The paper introduces a symbiotic architecture that equips large language models with audio‑understanding abilities without fine‑tuning their weights. It uses an injector module to write audio‑conditioned vectors into the LLM’s key‑value cache, allowing the model to act as an audio language model while keeping the backbone unchanged. The approach improves scalability—since injection cost depends on the injector width—and preserves the LLM’s original text performance, outperforming conventional frozen‑LLM methods and approaching fine‑tuned ALM results on audio tasks.
By Yotaro Kubo, Qi Sun, Yujin Tang
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
LLM-based agents have shown strong capabilities in automated data analysis and are increasingly moving toward long-horizon, multi-stage analytical workflows. However, as the analytical process evolves...
Text-to-image diffusion models enable data-efficient "mimicry" attacks, wherein adversaries fine-tune the model on a handful of public photos to synthesize convincing forgeries of a target individual....
The paper introduces OVIE, a monocular novel-view synthesis method that eliminates the need for multi‑view training data. By using a frozen depth estimator to generate pseudo‑target views from single images and applying masked and adversarial losses, OVIE is trained on 30 million uncurated images. It achieves state‑of‑the‑art performance on RealEstate10K and DL3DV, produces highly consistent multi‑view trajectories, and runs at 116 FPS—over 600× faster than the fastest baseline.
By Adrien Ramanana Rahary, Nicolas Dufour, Patrick Perez, David Picard
AlphaDiverse is a framework that enhances large language model–based multi‑agent systems for alpha factor mining by addressing cost, availability, and confidentiality constraints. It generates diverse research paths through varied environments and post‑training local agents, then fine‑tunes these agents with supervised learning and optimizes them jointly using a GRPO method that balances predictive quality and diversity. The approach limits research feedback to inner‑period data and evaluates a frozen model on outer‑period data to avoid test‑set tuning, demonstrating competitive prediction and broader exploration across four Chinese stock universes.
By Qingzhuo Wang, Zikun Wei, Zhihua Wei, Wen Shen
CinematicVQA is a new benchmark for evaluating large vision‑language models on film‑grammar reasoning. It introduces the Cinematic Scene Graph, a structured representation linking filming techniques to perceptual effects and narrative functions, and tests models on tasks beyond low‑level technique recognition. The study finds a semantic gap where models excel at describing visuals but struggle to identify underlying techniques, and shows that fine‑tuning improves performance on narrative function and multi‑hop reasoning.
By Shuo Xing, Pooja Verlani, Balu Adsumilli, Zhengzhong Tu
AV‑GRPO introduces a modality‑anchored diffusion reinforcement learning framework for joint audio‑video generation, addressing limitations in fidelity, text‑modality alignment, and cross‑modal synchronization. It decouples learning signals through modality‑anchored rollouts, employs trajectory‑locked frozen‑tower optimization to reduce computational cost, and adapts objectives to each modality’s dynamics. The accompanying 5DAV dataset provides difficulty‑controllable, decoupled training samples, and experiments on JavisBench and VABench show AV‑GRPO surpasses LTX‑2.3 in generation quality, semantic alignment, and synchronization.
By Zhiyu Xu, Weilong Yan, Yufei Shi, Shiyang Li, Yihao Liu, Kin-Man Lam, Yuewen Cao