EPIG-Tree proposes a compute‑optimal branching strategy for gradient‑efficient reinforcement learning, arguing that branches should be placed where they most reduce policy‑gradient uncertainty per unit of compute. By deriving allocation laws from a law‑of‑total‑variance decomposition, the method introduces an EPIG‑Tree score that guides branch placement using already computed rollouts, estimating occupancy‑ and score‑weighted value uncertainty. Empirical results show EPIG‑Tree reduces gradient MSE in cloned‑state control, improves frozen‑LLM gradient calibration, and outperforms flat GRPO and entropy branching in both single‑turn math and multi‑turn Wordle tasks.
By Nikita Khomich, Leopold Hermansson, Ido Hakimi
Astronex-World 1.0 is an open, controllable video world‑model foundation that can generate future visual states from text prompts or initial images, supporting frame‑aligned camera trajectories, continuous actions, and text events during rollout. It offers both a bidirectional model for full‑context generation and a causal model with block‑causal attention, built on the Wan2.2‑TI2V‑5B prior, and achieves real‑time 832×480 video at 24 fps. The model was trained over five stages on two NVIDIA L20 GPUs, scores 73.5 on WBench Navi and 70.0 on WBench Full, and outperforms several larger competitors while providing interfaces for embodied intelligence and autonomous driving.
By Xin Zhou, Cong Miao
The paper introduces a discriminative adaptation for SpeechLLMs that reads the hidden state of the final prompt token via a simple classification head, enabling emotion recognition in a single forward pass without altering the backbone. This approach replaces the generative decoder, which can produce out‑of‑set labels and favor frequent classes, with a controlled comparison between generative and discriminative inference. Experiments on IEMOCAP show improved Macro F1 scores, elimination of hallucinations, and larger gains on realistic ASR transcripts, while revealing that emotion directions encode indirect associations reflecting web‑scale text biases.
By Hasindri Watawana, Sergio Burdisso, Esa\'u Villatoro-Tello, Manjunath K E, Kadri Hacioglu, Petr Motlicek, Andreas Stolcke
The paper introduces SCRR-Net, a scene-conditioned spatial relation routing framework designed to forecast urban cellular activity by jointly modeling heterogeneous spatiotemporal signals such as SMS usage, mobile network traffic, and call activity. SCRR-Net integrates a context encoder, a spatial graph expert routing module, a temporal Transformer encoder, and a task knowledge routing module, allowing urban contextual information to control spatial dependency selection and cross-task knowledge transfer. Experiments on Milano and Trento datasets show that SCRR-Net consistently outperforms competing methods across all three forecasting tasks while offering interpretable routing behaviors.
By Qingzhong Li, Jingye Lin, Hui Ma, Yajun Zhang, Xinjun Pei, Ming Yan, Fei Xing
The paper introduces AttnPrint, a white‑box fingerprinting method that extracts low‑frequency components of cross‑modal attention distributions to identify multimodal large language models (MLLMs). It also presents DistillTrace, a black‑box auditing tool that uses hypothesis testing of MLLM outputs to detect potential model infringement. Experiments on 154 model instances across 19 architectures show that AttnPrint effectively detects derivative models and remains robust to downstream modifications, while DistillTrace reveals distillation relationships under various techniques.
By Chao Huang, Meng Tong, Kejiang Chen
Chronicle introduces a method called cut‑point replay to make regression testing of large language model (LLM) agents reproducible. It records an agent’s run at non‑deterministic boundaries as immutable envelopes and then replays selected boundaries while executing the rest live, enabling continuous‑integration tests that detect faulty code changes. Benchmarks show minimal overhead, perfect bit‑stability, and effective detection of unsafe actions in a mutation study.
By Tisha Chawla, Susheem Koul
oMeBench is a large-scale, expert-curated benchmark designed to evaluate large language models (LLMs) on organic mechanism reasoning. It contains over 10,000 annotated mechanistic steps, including reaction type labels, intermediate structures, and difficulty ratings, and introduces the oMeS scoring framework to assess logical consistency and chemical structural similarity. Evaluation shows that while current LLMs display promising chemical intuition, they often fail to produce correct and consistent multi-step reasoning, though prompting and fine-tuning can bring smaller models up to the level of closed‑source frontier models.
By Ruiling Xu, Yifan Zhang
The paper introduces NeuroCognition, a benchmark based on three neuropsychological tests—Raven's Progressive Matrices, Spatial Working Memory, and the Wisconsin Card Sorting Test—to evaluate foundational cognitive abilities in large language models (LLMs). It finds that while LLMs excel on text tasks, their performance drops on image-based and more complex tasks, and they fail different parts of the same tasks compared to humans. NeuroCognition correlates with standard general-capability benchmarks yet measures distinct cognitive skills, highlighting where LLMs align with or diverge from human-like intelligence.
By Faiz Ghifari Haznitrama, Faeyza Rishad Ardi, Alice Oh
FOCAL is a framework that aligns fine-grained ECG waveform segments with specific report tags using Optimal Transport, addressing the lack of localized representation in prior methods. It introduces a semantic similarity matrix to mitigate false negatives when reports share diagnoses, and a coarse‑to‑fine enrichment pipeline that employs Large Language Models to recover missing waveform semantics while filtering hallucinations. Experiments on six datasets show FOCAL achieves state‑of‑the‑art zero‑shot prediction and linear probing performance.
By Haitao Li, Che Liu, Zhengyao Ding, Ziyi Liu, Wenqi Shao, Zhengxing Huang
The paper adapts the compact PP‑OCRv6 recognizer for historical text recognition and compares it to a conventional CRNN across various training regimes, including generalized pretraining, domain‑specific training, corpus‑level fine‑tuning, and manuscript‑specific few‑shot adaptation on multilingual Latin and Arabic scripts. While PP‑OCRv6 does not always beat the CRNN when trained from scratch, heterogeneous pretraining significantly improves its generalization. Additionally, fine‑tuned PP‑OCRv6 can surpass a large vision‑language model (Qwen3.5‑based Medusa) that is specifically tailored for historical Latin‑script handwriting recognition.
By Benjamin Kiessling (ALMAnaCH)
MTF‑Net is a Multi‑Modal Temporal Feature Fusion Network that jointly models kinematic, appearance, and contextual cues for pedestrian intention prediction. It fuses four modalities—bounding‑box dynamics, human pose keypoints, local context, and scene‑level semantics—within a recurrent framework enhanced by gated linear units (GLUs) and an attention‑guided fusion head. Evaluations on the PIE and JAAD benchmarks show that MTF‑Net outperforms recent transformer‑ and graph‑based models, achieving up to 0.95 AUC on PIE and 0.94 AUC on JAAD while maintaining real‑time performance.
By Md Mahfuzur Rahman, Pengzhan Zhou, A. F. M. Abdun Noor, Md Imam Ahasan, Md Mustafizur Rahman, Fang Qu
The paper introduces BATON, a dual‑axis policy optimization framework for large language model agents that addresses two key aspects of reinforcement learning: intra‑trajectory feedback attribution and inter‑trajectory objective aggregation. BATON combines Bayesian Feedback Attribution, which builds a feedback‑conditioned posterior over sampled actions, with Trajectory Mass Normalization, which ensures equal optimization weight for complete trajectories. Experiments on ALFWorld, WebShop, and SearchQA demonstrate that each axis independently improves performance and that their combination yields the best results across different model scales.
By Yingxuan Zhuang, Binhe Yu, Jingxiao Yang, Ruopei Sun, Ziting Li, Cheng Tan, Xuhong Zhang, Jianwei Yin, Jintao Chen
The paper critiques the common practice of evaluating depth usage in depth‑recurrent language models by truncating depth during inference and measuring performance decline. It argues that this method conflates three distinct effects—fewer block applications, reduced computation, and an out‑of‑distribution readout—yet is usually interpreted as measuring only the second. To address this, the authors introduce the Depth Control Protocol (DCP), a suite of positive and negative controls that isolate each factor, along with a training intervention to confirm causality, specifically tailored for depth‑wise weight‑sharing architectures.
By Ha Van Dau, Thanh Tung Khuat, Nguyen Thanh Dung
arXiv:2609. 20519v1 Announce Type: new Abstract: As coding agents move from supervised code completion to unattended, around-the-clock exploration, their work expands from isolated predictions into long trajectories of reasoning, tool use, and feedback.
By Haozhe Liu, Tian Ye, Sensen Gao, Qihang Cao, Yitong Li, Mingchen Zhuge, Duomin Wang, Ruihua Zhang, Ping Luo, Jiawang Bian, Lei Zhu, Ligeng Zhu, Enze Xie, Song Han
The paper analyzes the environmental footprint of machine learning model training, focusing on large language models and their hardware. It finds that energy use and environmental impacts have risen exponentially over the past decade, even when employing carbon‑efficient electricity and more efficient hardware. The study argues that optimization strategies alone cannot curb these impacts due to a rebound effect, and stresses the need to evaluate hardware life‑cycle impacts and integrate environmental metrics into NLP research practices.
By Cl\'ement Morand (STL), Anne-Laure Ligozat (ENSIIE, LISN, STL), Aur\'elie N\'ev\'eol (STL, LISN)
The paper introduces an adaptive Mixture-of-Experts (MoE) framework for time series forecasting that incorporates expert-specific losses to give each expert a direct learning signal independent of gating weights. The overall objective combines base forecasting loss with these expert losses, encouraging experts to specialize on different temporal segments. A partial online learning strategy is added for efficient incremental updates, and experiments on economic, tourism, and energy datasets show the method outperforms state‑of‑the‑art neural models and foundation models, with ablation studies confirming the benefit of expert loss integration.
By Btissame El Mahtout, Florian Ziel
FakeSpotter is a new tool that estimates the viral misinformation risk of textual content by measuring structural fingerprints of misinformation instead of directly judging truthfulness. It operates across linguistic, narrative, logical, and critical‑thinking dimensions, using repeated large language model assessments and domain‑specific logistic regression classifiers for both short and long texts. In a labeled corpus of 764 texts, FakeSpotter achieved macro F1 scores of 0.788 for short texts and 0.793 for long texts, and its interpretive layer offers explainable outputs such as feature‑based scores, signal agreement, and a caution index for social listening.
By Giovanni Spitale, Federico Germani
The paper introduces D-Quant, a KV cache quantization framework that addresses the memory bottleneck of large language models by using a drift mechanism to convert entropy-coded representations into fixed-size bitstreams. This approach leverages the non-uniform distribution of KV cache values—after rotation and normalization, they approximate a normal distribution—allowing entropy coding to assign shorter codewords to frequent symbols while maintaining regular memory layouts suitable for parallel attention kernels. D-Quant thus aims to reduce memory footprint and bandwidth usage without sacrificing performance.
By Yi Su, Hong Liu, Guanghua Yu, Jianchen Zhu
The paper introduces pre‑trained models for extracting variant‑phenotype relations from biomedical text, focusing on the SNPPhenA corpus. Fine‑tuning small BERT‑based models, especially DeBERTa, achieves performance close to the current state‑of‑the‑art. Moreover, careful fine‑tuning of Google’s Gemini Pro 1.0 surpasses existing benchmarks on both sentence‑level and abstract‑level relation extraction tasks.
By Claudiu Creanga, Liviu P. Dinu, Daniela Gifu
The paper introduces SALR, a schema‑anchored latent reasoning approach for generating logical forms in knowledge‑base question answering. SALR delays explicit schema commitments by generating continuous thoughts in hidden states and aligns these thoughts with a codebook of KB schema elements, guided by an alignment objective derived from gold logical forms. Experiments on GrailQA and WebQSP demonstrate that SALR consistently outperforms strong baselines, notably improving compositional question performance by 2.86 F1 points over TIARA.
By Guangze Gao, Zixuan Li, Sikui Zhang, Chunfeng Yuan, Wenjuan Li, Bing Li, Xiaolong Jin, Weiming Hu