# Research Papers — 2026-01 · bundle page 129 of 189

> Full-text markdown of papers #6401–6450 of 9403 published in 2026-01, newest first. AI-readable mirrors of the full 9403-paper 2026-01 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2026-01/page/129
[← Previous bundle](https://aipod.dev/papers/archive/2026-01/page/128.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-01/page/130.md)

### A Multimodal Dataset of Student Oral Presentations with Sensors and Evaluation Data

Authors: Alvaro Becerra, Ruth Cobos, Roberto Daza
Published: 2026-01-12
Categories: cs.HC, cs.CV
arXiv: https://arxiv.org/abs/2601.07576v2

Oral presentation skills are a critical component of higher education, yet comprehensive datasets capturing real-world student performance across multiple modalities remain scarce. To address this gap, we present SOPHIAS (Student Oral Presentation monitoring for Holistic Insights & Analytics using Sensors), a 12-hour multimodal dataset containing recordings of 50 oral presentations delivered by 65 undergraduate and master's students at the Universidad Autonoma de Madrid, comprising 46 individual presentations with a mean presentation duration of 9 min 48 s (SD = 33 s) followed by a mean Q&A duration of 6 min 28 s (SD = 3 min 02 s), and 4 group presentations with a mean presentation duration of 14 min 11 s (SD = 1 min 40 s) followed by a mean Q&A duration of 8 min 22 s (SD = 1 min 21 s). SOPHIAS integrates eight timestamped sensor streams from high-definition webcams, ambient and webcam audio, eye-tracking glasses, smartwatch physiological sensors, and clicker, keyboard and mouse interactions. In addition, the dataset includes slides and rubric-based evaluations from teachers, peers, and self-assessments, along with timestamped contextual annotations. The dataset captures presentations conducted in real classroom settings, preserving authentic student behaviors, interactions, and physiological responses. SOPHIAS enables the exploration of relationships between multimodal behavioral and physiological signals and presentation performance, supports the study of peer-assessment and provides a benchmark for developing automated feedback and Multimodal Learning Analytics tools. The dataset is available for research, including both academic and legitimate commercial research and development, under controlled access through Science Data Bank, subject to approval of a Data Usage Agreement (DUA), with code provided through GitHub.

---

### A Model of Artificial Jagged Intelligence

Authors: Joshua Gans
Published: 2026-01-12
Categories: econ.TH, cs.AI
arXiv: https://arxiv.org/abs/2601.07573v1

Generative AI systems often display highly uneven performance across tasks that appear ``nearby'': they can be excellent on one prompt and confidently wrong on another with only small changes in wording or context. We call this phenomenon Artificial Jagged Intelligence (AJI). This paper develops a tractable economic model of AJI that treats adoption as an information problem: users care about \emph{local} reliability, but typically observe only coarse, global quality signals. In a baseline one-dimensional landscape, truth is a rough Brownian process, and the model ``knows'' scattered points drawn from a Poisson process. The model interpolates optimally, and the local error is measured by posterior variance. We derive an adoption threshold for a blind user, show that experienced errors are amplified by the inspection paradox, and interpret scaling laws as denser coverage that improves average quality without eliminating jaggedness. We then study mastery and calibration: a calibrated user who can condition on local uncertainty enjoys positive expected value even in domains that fail the blind adoption test. Modelling mastery as learning a reliability map via Gaussian process regression yields a learning-rate bound driven by information gain, clarifying when discovering ``where the model works'' is slow. Finally, we study how scaling interacts with discoverability: when calibrated signals and user mastery accelerate the harvesting of scale improvements, and when opacity can make gains from scaling effectively invisible.

---

### d3LLM: Ultra-Fast Diffusion LLM using Pseudo-Trajectory Distillation

Authors: Yu-Yang Qian, Junda Su, Lanxiang Hu, Peiyuan Zhang, Zhijie Deng, Peng Zhao, Hao Zhang
Published: 2026-01-12
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.07568v3

Diffusion large language models (dLLMs) offer capabilities beyond those of autoregressive (AR) LLMs, such as parallel decoding and random-order generation. However, realizing these benefits in practice is non-trivial, as dLLMs inherently face an accuracy-parallelism trade-off. Despite increasing interest, existing methods typically focus on only one-side of the coin, targeting either efficiency or accuracy. To address this limitation, we propose d3LLM (Pseudo-Distilled Diffusion Large Language Model), striking a balance between accuracy and parallelism: (i) during training, we introduce pseudo-trajectory distillation to teach the model which tokens can be decoded confidently at early steps, thereby improving parallelism; (ii) during inference, we employ entropy-based multi-block decoding with a KV-cache refresh mechanism to achieve high parallelism while maintaining accuracy. To better evaluate dLLMs, we also introduce AUP (Accuracy Under Parallelism), a new metric that jointly measures accuracy and parallelism. Experiments demonstrate that our d3LLM achieves up to 10$\times$ speedup over vanilla LLaDA/Dream, and 5$\times$ speedup over AR models without much accuracy drop. Our code is available at https://github.com/hao-ai-lab/d3LLM.

---

### Expert-Guided Multimodal Fusion for Unified Emotion and Sentiment Analysis

Authors: Jiaqi Qiao, Xinran Li, Yifan Lyu, Xiujuan Xu, Liu Yu
Published: 2026-01-12
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2601.07565v2

Multimodal emotion understanding requires the integration of heterogeneous data sources, including text, audio, and visual modalities, while simultaneously addressing discrete emotion recognition and continuous sentiment analysis. We propose EGMF, a unified framework that combines expert-guided multimodal fusion with large language models to achieve superior performance across both tasks. At the core of our framework is a multi-scale expert network, comprising a local expert for capturing subtle emotional nuances, a semantic correlation expert for modeling cross-modal relationships, and a global context expert for understanding long-range dependencies. These experts are adaptively integrated via hierarchical dynamic gating, enabling context-aware feature selection and modality weighting. The enhanced multimodal representations are seamlessly incorporated into the language model through pseudo token injection and prompt-based conditioning, allowing a single generative framework to handle both classification and regression tasks. We employ parameter-efficient LoRA fine-tuning to maintain computational efficiency. Extensive experiments on bilingual benchmark datasets (MELD, CHERMA, MOSEI, SIMS-V2) demonstrate that EGMF outperforms state-of-the-art methods in terms of accuracy, cross-lingual robustness, and the discovery of universal patterns in multimodal emotional expressions.

---

### Backpropagation-Free Test-Time Adaptation for Lightweight EEG-Based Brain-Computer Interfaces

Authors: Siyang Li, Jiayi Ouyang, Zhenyao Cui, Ziwei Wang, Tianwang Jia, Feng Wan, Dongrui Wu
Published: 2026-01-12
Categories: cs.HC, cs.AI
arXiv: https://arxiv.org/abs/2601.07556v3

Electroencephalogram (EEG)-based brain-computer interfaces (BCIs) face significant deployment challenges due to inter-subject variability, signal non-stationarity, and computational constraints. While test-time adaptation (TTA) mitigates distribution shifts under online data streams without per-use calibration sessions, existing TTA approaches heavily rely on explicitly defined loss objectives that require backpropagation for updating model parameters, which incurs computational overhead, privacy risks, and sensitivity to noisy data streams. This paper proposes Backpropagation-Free Transformations (BFT), a TTA approach for EEG decoding that avoids these issues. BFT applies multiple sample-wise transformations, based on knowledge-guided augmentations or structured feature masking, to each test trial, producing multiple predictions for a single test sample using only forward passes. A learning-to-rank module, trained on source data, estimates the reliability of each transformed prediction, so that a weighted aggregation suppresses prediction uncertainty during online inference, with theoretical justification. Extensive experiments on five EEG datasets, covering motor imagery classification and driver drowsiness regression, demonstrate the effectiveness, versatility, robustness, and efficiency of BFT. This research enables lightweight plug-and-play BCIs on resource-constrained devices, broadening the real-world deployment of EEG-based BCIs.

---

### VirtualEnv: A Platform for Embodied AI Research

Authors: Kabir Swain, Sijie Han, Ayush Raina, Jin Zhang, Shuang Li, Michael Stopa, Antonio Torralba
Published: 2026-01-12
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.07553v2

As large language models (LLMs) continue to improve in reasoning and decision-making, there is a growing need for realistic and interactive environments where their abilities can be rigorously evaluated. We present VirtualEnv, a next-generation simulation platform built on Unreal Engine 5 that enables fine-grained benchmarking of LLMs in embodied and interactive scenarios. VirtualEnv supports rich agent-environment interactions, including object manipulation, navigation, and adaptive multi-agent collaboration, as well as game-inspired mechanics like escape rooms and procedurally generated environments. We provide a user-friendly API built on top of Unreal Engine, allowing researchers to deploy and control LLM-driven agents using natural language instructions. We integrate large-scale LLMs and vision-language models (VLMs), such as GPT-based models, to generate novel environments and structured tasks from multimodal inputs. Our experiments benchmark the performance of several popular LLMs across tasks of increasing complexity, analyzing differences in adaptability, planning, and multi-agent coordination. We also describe our methodology for procedural task generation, task validation, and real-time environment control. VirtualEnv is released as an open-source platform, we aim to advance research at the intersection of AI and gaming, enable standardized evaluation of LLMs in embodied AI settings, and pave the way for future developments in immersive simulations and interactive entertainment.

---

### TFEC: Multivariate Time-Series Clustering via Temporal-Frequency Enhanced Contrastive Learning

Authors: Zexi Tan, Tao Xie, Haoyi Xiao, Baoyao Yang, Yuzhu Ji, An Zeng, Xiang Zhang, Yiqun Zhang
Published: 2026-01-12
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.07550v1

Multivariate Time-Series (MTS) clustering is crucial for signal processing and data analysis. Although deep learning approaches, particularly those leveraging Contrastive Learning (CL), are prominent for MTS representation, existing CL-based models face two key limitations: 1) neglecting clustering information during positive/negative sample pair construction, and 2) introducing unreasonable inductive biases, e.g., destroying time dependence and periodicity through augmentation strategies, compromising representation quality. This paper, therefore, proposes a Temporal-Frequency Enhanced Contrastive (TFEC) learning framework. To preserve temporal structure while generating low-distortion representations, a temporal-frequency Co-EnHancement (CoEH) mechanism is introduced. Accordingly, a synergistic dual-path representation and cluster distribution learning framework is designed to jointly optimize cluster structure and representation fidelity. Experiments on six real-world benchmark datasets demonstrate TFEC's superiority, achieving 4.48% average NMI gains over SOTA methods, with ablation studies validating the design. The code of the paper is available at: https://github.com/yueliangy/TFEC.

---

### Contextual Discrepancy-Aware Contrastive Learning for Robust Medical Time Series Diagnosis in Small-Sample Scenarios

Authors: Kaito Tanaka, Aya Nakayama, Masato Ito, Yuji Nishimura, Keisuke Matsuda
Published: 2026-01-12
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.07548v1

Medical time series data, such as EEG and ECG, are vital for diagnosing neurological and cardiovascular diseases. However, their precise interpretation faces significant challenges due to high annotation costs, leading to data scarcity, and the limitations of traditional contrastive learning in capturing complex temporal patterns. To address these issues, we propose CoDAC (Contextual Discrepancy-Aware Contrastive learning), a novel framework that enhances diagnostic accuracy and generalization, particularly in small-sample settings. CoDAC leverages external healthy data and introduces a Contextual Discrepancy Estimator (CDE), built upon a Transformer-based Autoencoder, to precisely quantify abnormal signals through context-aware anomaly scores. These scores dynamically inform a Dynamic Multi-views Contrastive Framework (DMCF), which adaptively weights different temporal views to focus contrastive learning on diagnostically relevant, discrepant regions. Our encoder combines dilated convolutions with multi-head attention for robust feature extraction. Comprehensive experiments on Alzheimer's Disease EEG, Parkinson's Disease EEG, and Myocardial Infarction ECG datasets demonstrate CoDAC's superior performance across all metrics, consistently outperforming state-of-the-art baselines, especially under low label availability. Ablation studies further validate the critical contributions of CDE and DMCF. CoDAC offers a robust and interpretable solution for medical time series diagnosis, effectively mitigating data scarcity challenges.

---

### Near-Optimal Private Linear Regression via Iterative Hessian Mixing

Authors: Omri Lev, Moshe Shenfeld, Vishwak Srinivasan, Katrina Ligett, Ashia C. Wilson
Published: 2026-01-12
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2601.07545v2

We study differentially private ordinary least squares (DP-OLS) with bounded data $(X,Y)$ via sketching-based mechanisms. While Gaussian sketching approaches have been explored for DP-OLS \citep{sheffet2017differentially}, they are typically viewed as less competitive than the Adaptive Sufficient Statistics Perturbation (AdaSSP) method \citep{wang_adassp}, which directly perturbs the sufficient statistics $(X^{\top}X, X^{\top}Y)$. This method was shown to be close to information-theoretically optimal, while also exhibiting strong empirical performance. In this work, we propose the \emph{Iterative Hessian Mixing} (IHM), an algorithm that builds on Gaussian sketching approaches to DP-OLS and is inspired by the Iterative Hessian Sketch of \citet{pilanci_hessiansketch}. We prove that IHM is differentially private and provide utility guarantees in the form of excess empirical risk bounds. These bounds improve upon those of AdaSSP by removing a multiplicative factor that can be as large as the square root of the data dimension. The design of the IHM is based on new accuracy guarantees that we present for prior Gaussian sketching approaches for DP-OLS, which clarify when these methods are expected to perform well and how IHM circumvents their inherent limitations. We also conduct a rigorous empirical evaluation on a large suite of datasets, demonstrating that IHM consistently outperforms prior baselines, including AdaSSP.

---

### Enhancing Novel View Synthesis via Geometry Grounded Set Diffusion

Authors: Farhad G. Zanjani, Hong Cai, Amirhossein Habibian
Published: 2026-01-12
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.07540v3

We present SetDiff, a geometry-grounded multi-view diffusion framework that enhances novel-view renderings produced by 3D Gaussian Splatting. Our method integrates explicit 3D priors, pixel-aligned coordinate maps and pose-aware Plucker ray embeddings, into a set-based diffusion model capable of jointly processing variable numbers of reference and target views. This formulation enables robust occlusion handling, reduces hallucinations under low-signal conditions, and improves photometric fidelity in visual content restoration. A unified set mixer performs global token-level attention across all input views, supporting scalable multi-camera enhancement while maintaining computational efficiency through latent-space supervision and selective decoding. Extensive experiments on EUVS, Para-Lane, nuScenes, and DL3DV demonstrate significant gains in perceptual fidelity, structural similarity, and robustness under severe extrapolation. SetDiff establishes a state-of-the-art diffusion-based solution for realistic and reliable novel-view synthesis in autonomous driving scenarios.

---

### Nonparametric Kernel Clustering with Bandit Feedback

Authors: Victor Thuot, Sebastian Vogt, Debarghya Ghoshdastidar, Nicolas Verzelen
Published: 2026-01-12
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2601.07535v1

Clustering with bandit feedback refers to the problem of partitioning a set of items, where the clustering algorithm can sequentially query the items to receive noisy observations. The problem is formally posed as the task of partitioning the arms of an N-armed stochastic bandit according to their underlying distributions, grouping two arms together if and only if they share the same distribution, using samples collected sequentially and adaptively. This setting has gained attention in recent years due to its applicability in recommendation systems and crowdsourcing. Existing works on clustering with bandit feedback rely on a strong assumption that the underlying distributions are sub-Gaussian. As a consequence, the existing methods mainly cover settings with linearly-separable clusters, which has little practical relevance. We introduce a framework of ``nonparametric clustering with bandit feedback'', where the underlying arm distributions are not constrained to any parametric, and hence, it is applicable for active clustering of real-world datasets. We adopt a kernel-based approach, which allows us to reformulate the nonparametric problem as the task of clustering the arms according to their kernel mean embeddings in a reproducing kernel Hilbert space (RKHS). Building on this formulation, we introduce the KABC algorithm with theoretical correctness guarantees and analyze its sampling budget. We introduce a notion of signal-to-noise ratio for this problem that depends on the maximum mean discrepancy (MMD) between the arm distributions and on their variance in the RKHS. Our algorithm is adaptive to this unknown quantity: it does not require it as an input yet achieves instance-dependent guarantees.

---

### Loci Similes: A Benchmark for Extracting Intertextualities in Latin Literature

Authors: Julian Schelb, Michael Wittweiler, Marie Revellio, Barbara Feichtinger, Andreas Spitz
Published: 2026-01-12
Categories: cs.IR, cs.CL, cs.DL
arXiv: https://arxiv.org/abs/2601.07533v3

Tracing connections between historical texts is an important part of intertextual research, enabling scholars to reconstruct the virtual library of a writer and identify the sources influencing their creative process. These intertextual links manifest in diverse forms, ranging from direct verbatim quotations to subtle allusions and paraphrases disguised by morphological variation. Language models offer a promising path forward due to their capability of capturing semantic similarity beyond lexical overlap. However, the development of new methods for this task is held back by the scarcity of standardized benchmarks and easy-to-use datasets. We address this gap by introducing Loci Similes, a benchmark for Latin intertextuality detection comprising a curated dataset of ~176k text segments and 1,490 expert-verified parallels, including 945 labeled references from an existing dataset. Using this data, we establish baselines for retrieval and classification of intertextualities with both lexical methods and pretrained encoder language models.

---

### From RAG to Agentic RAG for Faithful Islamic Question Answering

Authors: Gagan Bhatia, Hamdy Mubarak, Mustafa Jarrar, George Mikros, Fadi Zaraket, Mahmoud Alhirthani, Mutaz Al-Khatib, Logan Cochrane, Kareem Darwish, Rashid Yahiaoui, Firoj Alam
Published: 2026-01-12
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2601.07528v2

Large Language Models (LLMs) are increasingly used for Islamic question answering, where ungrounded responses may carry serious religious consequences. Yet standard MCQ/MRC-style evaluations (MCQ: Multiple choice questions, MRC: Machine Reading Comprehension) do not capture key real-world failure modes, notably free-form hallucinations and the ability to abstain when evidence is insufficient. To address this gap, we introduce IslamicFaithQA, a 3,810-item bilingual (Arabic/English) generative benchmark with atomic single-gold answers, which enables direct measurement of hallucination and abstention. We additionally developed an end-to-end grounded Islamic modeling suite consisting of (i) 25K Arabic text-grounded SFT reasoning pairs, (ii) 5K bilingual preference samples for reward-guided alignment, and (iii) a verse-level Qur'an retrieval corpus of ~6k atomic verses (ayat). Building on these resources, we develop an agentic Quran-grounding framework (agentic RAG) that uses structured tool calls for iterative evidence seeking and answer revision. Experiments across Arabic-centric and multilingual LLMs show that retrieval improves correctness and that agentic RAG yields the largest gains beyond standard RAG, achieving state-of-the-art performance and stronger Arabic-English robustness even with a small model (i.e., Qwen3 4B). We made the datasets are publicly available. https://huggingface.co/datasets/QCRI/IslamicFaithQA

---

### Thinking Before Constraining: A Unified Decoding Framework for Large Language Models

Authors: Ngoc Trinh Hung Nguyen, Alonso Silva, Laith Zumot, Liubov Tupikina, Armen Aghasaryan, Mehwish Alam
Published: 2026-01-12
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2601.07525v2

Natural generation allows Large Language Models (LLMs) to produce free-form responses with rich reasoning, yet the lack of structure makes outputs difficult to verify. Conversely, constrained decoding ensures standardized formats but can inadvertently restrict reasoning capabilities by imposing constraints too early in the generation process. We propose a hybrid approach, namely In-Writing, that combines free-form reasoning and structured generation in a single call. The model first performs unconstrained reasoning and only applies structured decoding after a trigger token is generated, explicitly decoupling reasoning from formatting. We establish that our trigger-token strategies are able to virtually eradicate premature triggering, a failure mode in which constrained decoding interrupts on-going reasoning. Evaluations across diverse datasets covering classification and reasoning tasks demonstrate that our approach outperforms the state-of-the-art by achieving accuracy gains of up to 27% over natural generation. Our code are available at: https://github.com/Nokia-Bell-Labs/InWriting.

---

### Stagewise Reinforcement Learning and the Geometry of the Regret Landscape

Authors: Chris Elliott, Einar Urdshals, David Quarel, Matthew Farrugia-Roberts, Daniel Murfet
Published: 2026-01-12
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.07524v2

Singular learning theory characterizes Bayesian learning as an evolving tradeoff between accuracy and complexity, with transitions between qualitatively different solutions as sample size increases. We extend this theory to reinforcement learning, proving that the concentration of a generalized posterior over policies is governed by the local learning coefficient (LLC), an invariant of the geometry of the regret function. This theory predicts that deep reinforcement learning with SGD should proceed from simple policies with high regret to complex policies with low regret. We verify this prediction empirically in a gridworld environment exhibiting stagewise policy development: phase transitions over training manifest as "opposing staircases" where regret decreases sharply while the LLC increases.

---

### cSVR: Convolutional Slice-to-Volume Reconstruction

Authors: Margherita Firenze, Sean I. Young, Clinton J. Wang, Hyuk Jin Yun, Elfar Adalsteinsson, Kiho Im, P. Ellen Grant, Polina Golland
Published: 2026-01-12
Categories: eess.IV, cs.CV
arXiv: https://arxiv.org/abs/2601.07519v2

Unpredictable fetal motion during MRI scans can result in oblique 2D slices that are difficult to interpret and often leads to prolonged scan times. Slice-to-volume reconstruction (SVR) methods align 2D oblique slices from multiple slice stacks into a coherent 3D volume. We propose a convolutional network that predicts slice poses by performing multiscale, unrolled optimization and further refines them and super-resolves the volume using model-based optimization. Our convolutional feed-forward SVR network achieves accuracy on par with state-of-the-art results while offering significant speedup, paving the way for scanner-side use of SVR. The code is available https://github.com/MedicalVisionGroup/cSVR.

---

### Mon3tr: Monocular 3D Telepresence with Pre-built Gaussian Avatars as Amortization

Authors: Fangyu Lin, Yingdong Hu, Zhening Liu, Yufan Zhuang, Zehong Lin, Jun Zhang
Published: 2026-01-12
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2601.07518v1

Immersive telepresence aims to transform human interaction in AR/VR applications by enabling lifelike full-body holographic representations for enhanced remote collaboration. However, existing systems rely on hardware-intensive multi-camera setups and demand high bandwidth for volumetric streaming, limiting their real-time performance on mobile devices. To overcome these challenges, we propose Mon3tr, a novel Monocular 3D telepresence framework that integrates 3D Gaussian splatting (3DGS) based parametric human modeling into telepresence for the first time. Mon3tr adopts an amortized computation strategy, dividing the process into a one-time offline multi-view reconstruction phase to build a user-specific avatar and a monocular online inference phase during live telepresence sessions. A single monocular RGB camera is used to capture body motions and facial expressions in real time to drive the 3DGS-based parametric human model, significantly reducing system complexity and cost. The extracted motion and appearance features are transmitted at < 0.2 Mbps over WebRTC's data channel, allowing robust adaptation to network fluctuations. On the receiver side, e.g., Meta Quest 3, we develop a lightweight 3DGS attribute deformation network to dynamically generate corrective 3DGS attribute adjustments on the pre-built avatar, synthesizing photorealistic motion and appearance at ~ 60 FPS. Extensive experiments demonstrate the state-of-the-art performance of our method, achieving a PSNR of > 28 dB for novel poses, an end-to-end latency of ~ 80 ms, and > 1000x bandwidth reduction compared to point-cloud streaming, while supporting real-time operation from monocular inputs across diverse scenarios. Our demos can be found at https://mon3tr3d.github.io.

---

### Controlling Multimodal Conversational Agents with Coverage-Enhanced Latent Actions

Authors: Yongqi Li, Hao Lang, Tieyun Qian, Yongbin Li
Published: 2026-01-12
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2601.07516v2

Vision-language models are increasingly employed as multimodal conversational agents (MCAs) for diverse conversational tasks. Recently, reinforcement learning (RL) has been widely explored for adapting MCAs to various human-AI interaction scenarios. Despite showing great enhancement in generalization performance, fine-tuning MCAs via RL still faces challenges in handling the extremely large text token space. To address this, we learn a compact latent action space for RL fine-tuning instead. Specifically, we adopt the learning from observation mechanism to construct the codebook for the latent action space, where future observations are leveraged to estimate current latent actions that could further be used to reconstruct future observations. However, the scarcity of paired image-text data hinders learning a codebook with sufficient coverage. Thus, we leverage both paired image-text data and text-only data to construct the latent action space, using a cross-modal projector for transforming text embeddings into image-text embeddings. We initialize the cross-modal projector on paired image-text data, and further train it on massive text-only data with a novel cycle consistency loss to enhance its robustness. We show that our latent action based method outperforms competitive baselines on two conversation tasks across various RL algorithms.

---

### Data-Driven Stochastic VRP: Integration of Forecast Duration into Optimization for Utility Workforce Management

Authors: Matteo Garbelli
Published: 2026-01-12
Categories: math.OC, cs.AI
arXiv: https://arxiv.org/abs/2601.07514v1

This paper investigates the integration of machine learning forecasts of intervention durations into a stochastic variant of the Capacitated Vehicle Routing Problem with Time Windows (CVRPTW). In particular, we exploit tree-based gradient boosting (XGBoost) trained on eight years of gas meter maintenance data to produce point predictions and uncertainty estimates, which then drive a multi-objective evolutionary optimization routine. The methodology addresses uncertainty through sub-Gaussian concentration bounds for route-level risk buffers and explicitly accounts for competing operational KPIs through a multi-objective formulation. Empirical analysis of prediction residuals validates the sub-Gaussian assumption underlying the risk model. From an empirical point of view, our results report improvements around 20-25\% in operator utilization and completion rates compared with plans computed using default durations. The integration of uncertainty quantification and risk-aware optimization provides a practical framework for handling stochastic service durations in real-world routing applications.

---

### Land-then-transport: A Flow Matching-Based Generative Decoder for Wireless Image Transmission

Authors: Jingwen Fu, Ming Xiao, Mikael Skoglund, Dong In Kim
Published: 2026-01-12
Categories: cs.LG, eess.IV
arXiv: https://arxiv.org/abs/2601.07512v1

Due to strict rate and reliability demands, wireless image transmission remains difficult for both classical layered designs and joint source-channel coding (JSCC), especially under low latency. Diffusion-based generative decoders can deliver strong perceptual quality by leveraging learned image priors, but iterative stochastic denoising leads to high decoding delay. To enable low-latency decoding, we propose a flow-matching (FM) generative decoder under a new land-then-transport (LTT) paradigm that tightly integrates the physical wireless channel into a continuous-time probability flow. For AWGN channels, we build a Gaussian smoothing path whose noise schedule indexes effective noise levels, and derive a closed-form teacher velocity field along this path. A neural-network student vector field is trained by conditional flow matching, yielding a deterministic, channel-aware ODE decoder with complexity linear in the number of ODE steps. At inference, it only needs an estimate of the effective noise variance to set the ODE starting time. We further show that Rayleigh fading and MIMO channels can be mapped, via linear MMSE equalization and singular-value-domain processing, to AWGN-equivalent channels with calibrated starting times. Therefore, the same probability path and trained velocity field can be reused for Rayleigh and MIMO without retraining. Experiments on MNIST, Fashion-MNIST, and DIV2K over AWGN, Rayleigh, and MIMO demonstrate consistent gains over JPEG2000+LDPC, DeepJSCC, and diffusion-based baselines, while achieving good perceptual quality with only a few ODE steps. Overall, LTT provides a deterministic, physically interpretable, and computation-efficient framework for generative wireless image decoding across diverse channels.

---

### High-Rank Structured Modulation for Parameter-Efficient Fine-Tuning

Authors: Yongkang Liu, Xing Li, Mengjie Zhao, Shanru Zhang, Zijing Wang, Qian Li, Shi Feng, Feiliang Ren, Daling Wang, Hinrich Schütze
Published: 2026-01-12
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.07507v1

As the number of model parameters increases, parameter-efficient fine-tuning (PEFT) has become the go-to choice for tailoring pre-trained large language models. Low-rank Adaptation (LoRA) uses a low-rank update method to simulate full parameter fine-tuning, which is widely used to reduce resource requirements. However, decreasing the rank encounters challenges with limited representational capacity when compared to full parameter fine-tuning. We present \textbf{SMoA}, a high-rank \textbf{S}tructured \textbf{MO}dulation \textbf{A}dapter that uses fewer trainable parameters while maintaining a higher rank, thereby improving the model's representational capacity and offering improved performance potential. The core idea is to freeze the original pretrained weights and selectively amplify or suppress important features of the original weights across multiple subspaces. The subspace mechanism provides an efficient way to increase the capacity and complexity of a model. We conduct both theoretical analyses and empirical studies on various tasks. Experiment results show that SMoA outperforms LoRA and its variants on 10 tasks, with extensive ablation studies validating its effectiveness.

---

### Judging Against the Reference: Uncovering Knowledge-Driven Failures in LLM-Judges on QA Evaluation

Authors: Dongryeol Lee, Yerin Hwang, Taegwan Kang, Minwoo Lee, Younhyung Chae, Kyomin Jung
Published: 2026-01-12
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.07506v2

While large language models (LLMs) are increasingly used as automatic judges for question answering (QA) and other reference-conditioned evaluation tasks, little is known about their ability to adhere to a provided reference. We identify a critical failure mode of such reference-based LLM QA evaluation: when the provided reference conflicts with the judge model's parametric knowledge, the resulting scores become unreliable, substantially degrading evaluation fidelity. To study this phenomenon systematically, we introduce a controlled swapped-reference QA framework that induces reference-belief conflicts. Specifically, we replace the reference answer with an incorrect entity and construct diverse pairings of original and swapped references with correspondingly aligned candidate answers. Surprisingly, grading reliability drops sharply under swapped references across a broad set of judge models. We empirically show that this vulnerability is driven by judges' over-reliance on parametric knowledge, leading judges to disregard the given reference under conflict. Finally, we find that this failure persists under common prompt-based mitigation strategies, highlighting a fundamental limitation of LLM-as-a-judge evaluation and motivating reference-based protocols that enforce stronger adherence to the provided reference.

---

### FROAV: A Framework for RAG Observation and Agent Verification -- Lowering the Barrier to LLM Agent Research

Authors: Tzu-Hsuan Lin, Chih-Hsuan Kao
Published: 2026-01-12
Categories: cs.LG, cs.SE
arXiv: https://arxiv.org/abs/2601.07504v1

The rapid advancement of Large Language Models (LLMs) and their integration into autonomous agent systems has created unprecedented opportunities for document analysis, decision support, and knowledge retrieval. However, the complexity of developing, evaluating, and iterating on LLM-based agent workflows presents significant barriers to researchers, particularly those without extensive software engineering expertise. We present FROAV (Framework for RAG Observation and Agent Verification), an open-source research platform that democratizes LLM agent research by providing a plug-and-play architecture combining visual workflow orchestration, a comprehensive evaluation framework, and extensible Python integration. FROAV implements a multi-stage Retrieval-Augmented Generation (RAG) pipeline coupled with a rigorous "LLM-as-a-Judge" evaluation system, all accessible through intuitive graphical interfaces. Our framework integrates n8n for no-code workflow design, PostgreSQL for granular data management, FastAPI for flexible backend logic, and Streamlit for human-in-the-loop interaction. Through this integrated ecosystem, researchers can rapidly prototype RAG strategies, conduct prompt engineering experiments, validate agent performance against human judgments, and collect structured feedback-all without writing infrastructure code. We demonstrate the framework's utility through its application to financial document analysis, while emphasizing its material-agnostic architecture that adapts to any domain requiring semantic analysis. FROAV represents a significant step toward making LLM agent research accessible to a broader scientific community, enabling researchers to focus on hypothesis testing and algorithmic innovation rather than system integration challenges.

---

### Anatomy Aware Cascade Network: Bridging Epistemic Uncertainty and Geometric Manifold for 3D Tooth Segmentation

Authors: Bing Yu, Liu Shi, Haitao Wang, Deran Qi, Xiang Cai, Wei Zhong, Qiegen Liu
Published: 2026-01-12
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.07499v1

Accurate three-dimensional (3D) tooth segmentation from Cone-Beam Computed Tomography (CBCT) is a prerequisite for digital dental workflows. However, achieving high-fidelity segmentation remains challenging due to adhesion artifacts in naturally occluded scans, which are caused by low contrast and indistinct inter-arch boundaries. To address these limitations, we propose the Anatomy Aware Cascade Network (AACNet), a coarse-to-fine framework designed to resolve boundary ambiguity while maintaining global structural consistency. Specifically, we introduce two mechanisms: the Ambiguity Gated Boundary Refiner (AGBR) and the Signed Distance Map guided Anatomical Attention (SDMAA). The AGBR employs an entropy based gating mechanism to perform targeted feature rectification in high uncertainty transition zones. Meanwhile, the SDMAA integrates implicit geometric constraints via signed distance map to enforce topological consistency, preventing the loss of spatial details associated with standard pooling. Experimental results on a dataset of 125 CBCT volumes demonstrate that AACNet achieves a Dice Similarity Coefficient of 90.17 \% and a 95\% Hausdorff Distance of 3.63 mm, significantly outperforming state-of-the-art methods. Furthermore, the model exhibits strong generalization on an external dataset with an HD95 of 2.19 mm, validating its reliability for downstream clinical applications such as surgical planning. Code for AACNet is available at https://github.com/shiliu0114/AACNet.

---

### Graph Inference Towards ICD Coding

Authors: Xiaoxiao Deng
Published: 2026-01-12
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.07496v1

Automated ICD coding involves assigning standardized diagnostic codes to clinical narratives. The vast label space and extreme class imbalance continue to challenge precise prediction. To address these issues, LabGraph is introduced -- a unified framework that reformulates ICD coding as a graph generation task. By combining adversarial domain adaptation, graph-based reinforcement learning, and perturbation regularization, LabGraph effectively enhances model robustness and generalization. In addition, a label graph discriminator dynamically evaluates each generated code, providing adaptive reward feedback during training. Experiments on benchmark datasets demonstrate that LabGraph consistently outperforms previous approaches on micro-F1, micro-AUC, and P@K.

---

### Online Markov Decision Processes with Terminal Law Constraints

Authors: Bianca Marin Moreno, Margaux Brégère, Pierre Gaillard, Nadia Oudjane
Published: 2026-01-12
Categories: math.OC, stat.ML
arXiv: https://arxiv.org/abs/2601.07492v1

Traditional reinforcement learning usually assumes either episodic interactions with resets or continuous operation to minimize average or cumulative loss. While episodic settings have many theoretical results, resets are often unrealistic in practice. The infinite-horizon setting avoids this issue but lacks non-asymptotic guarantees in online scenarios with unknown dynamics. In this work, we move towards closing this gap by introducing a reset-free framework called the periodic framework, where the goal is to find periodic policies: policies that not only minimize cumulative loss but also return the agents to their initial state distribution after a fixed number of steps. We formalize the problem of finding optimal periodic policies and identify sufficient conditions under which it is well-defined for tabular Markov decision processes. To evaluate algorithms in this framework, we introduce the periodic regret, a measure that balances cumulative loss with the terminal law constraint. We then propose the first algorithms for computing periodic policies in two multi-agent settings and show they achieve sublinear periodic regret of order $\tilde O(T^{3/4})$. This provides the first non-asymptotic guarantees for reset-free learning in the setting of $M$ homogeneous agents, for $M > 1$.

---

### FocalOrder: Focal Preference Optimization for Reading Order Detection

Authors: Fuyuan Liu, Dianyu Yu, He Ren, Nayu Liu, Xiaomian Kang, Delai Qiu, Fa Zhang, Genpeng Zhen, Shengping Liu, Jiaen Liang, Wei Huang, Yining Wang et al.
Published: 2026-01-12
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.07483v1

Reading order detection is the foundation of document understanding. Most existing methods rely on uniform supervision, implicitly assuming a constant difficulty distribution across layout regions. In this work, we challenge this assumption by revealing a critical flaw: \textbf{Positional Disparity}, a phenomenon where models demonstrate mastery over the deterministic start and end regions but suffer a performance collapse in the complex intermediate sections. This degradation arises because standard training allows the massive volume of easy patterns to drown out the learning signals from difficult layouts. To address this, we propose \textbf{FocalOrder}, a framework driven by \textbf{Focal Preference Optimization (FPO)}. Specifically, FocalOrder employs adaptive difficulty discovery with exponential moving average mechanism to dynamically pinpoint hard-to-learn transitions, while introducing a difficulty-calibrated pairwise ranking objective to enforce global logical consistency. Extensive experiments demonstrate that FocalOrder establishes new state-of-the-art results on OmniDocBench v1.0 and Comp-HRDoc. Our compact model not only outperforms competitive specialized baselines but also significantly surpasses large-scale general VLMs. These results demonstrate that aligning the optimization with intrinsic structural ambiguity of documents is critical for mastering complex document structures.

---

### The Secretary Problem with Predictions and a Chosen Order

Authors: Helia Karisani, Mohammadreza Daneshvaramoli, Hedyeh Beyhaghi, Mohammad Hajiesmaili, Cameron Musco
Published: 2026-01-12
Categories: cs.DS, cs.DM, cs.GT, cs.LG
arXiv: https://arxiv.org/abs/2601.07482v1

We study a learning-augmented variant of the secretary problem, recently introduced by Fujii and Yoshida (2023), in which the decision-maker has access to machine-learned predictions of candidate values. The central challenge is to balance consistency and robustness: when predictions are accurate, the algorithm should select a near-optimal secretary, while under inaccurate predictions it should still guarantee a bounded competitive ratio. We consider both the classical Random Order Secretary Problem (ROSP), where candidates arrive in a uniformly random order, and a more natural learning-augmented model in which the decision-maker may choose the arrival order based on predicted values. We call this model the Chosen Order Secretary Problem (COSP), capturing scenarios such as interview schedules set in advance. We propose a new randomized algorithm applicable to both ROSP and COSP. Our method switches from fully trusting predictions to a threshold-based rule once a large prediction deviation is detected. Let $ε\in (0,1)$ denote the maximum multiplicative prediction error. For ROSP, our algorithm achieves a competitive ratio of $\max\{0.221, (1-ε)/(1+ε)\}$, improving upon the prior bound of $\max\{0.215, (1-ε)/(1+ε)\}$. For COSP, we achieve $\max\{0.262, (1-ε)/(1+ε)\}$, surpassing the $0.25$ worst-case bound for prior approaches and moving closer to the classical secretary benchmark of $1/e \approx 0.368$. These results highlight the benefit of combining predictions with arrival-order control in online decision-making.

---

### JudgeFlow: Agentic Workflow Optimization via Block Judge

Authors: Zihan Ma, Zhikai Zhao, Chuanbo Hua, Federico Berto, Jinkyoo Park
Published: 2026-01-12
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.07477v2

Optimizing LLM-based agentic workflows is challenging for scaling AI capabilities. Current methods rely on coarse, end-to-end evaluation signals and lack fine-grained signals on where to refine, often resulting in inefficient or low-impact modifications. To address these limitations, we propose JudgeFlow, an Evaluation-Judge-Optimization-Update pipeline. We incorporate reusable, configurable logic blocks into agentic workflows to capture fundamental forms of logic. On top of this abstraction, we design a dedicated Judge module that inspects execution traces particularly failed runs and assigns rank-based responsibility scores to problematic blocks. These fine-grained diagnostic signals are then leveraged by an LLM-based optimizer, which focuses modifications on the most problematic block in the workflow. Our approach improves sample efficiency, enhances interpretability through block-level diagnostics, and provides a scalable foundation for automating increasingly complex agentic workflows. We evaluate JudgeFlow on mathematical reasoning and code generation benchmarks, where JudgeFlow achieves superior performance and efficiency compared to existing methods.

---

### ARCQuant: Boosting NVFP4 Quantization with Augmented Residual Channels for LLMs

Authors: Haoqian Meng, Yilun Luo, Yafei Zhao, Wenyuan Liu, Peng Zhang, Xindian Ma
Published: 2026-01-12
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.07475v2

The emergence of fine-grained numerical formats like NVFP4 presents new opportunities for efficient Large Language Model (LLM) inference. However, it is difficult to adapt existing Post-Training Quantization (PTQ) strategies to these formats: rotation-based methods compromise fine-grained block isolation; smoothing techniques struggle with significant 4-bit quantization errors; and mixed-precision approaches often conflict with hardware constraints on unified-precision computation. To address these challenges, we propose ARCQuant, a framework that boosts NVFP4 performance via Augmented Residual Channels. Distinct from methods that compromise block isolation or hardware uniformity, ARCQuant maintains a strictly unified NVFP4 format by augmenting the activation matrix with quantized residual channels. This design integrates the error compensation process directly into the matrix reduction dimension, enabling the use of standard, highly optimized GEMM kernels with minimal overhead. Theoretical analysis confirms that the worst-case error bound of our dual-stage NVFP4 quantization is comparable to that of standard 8-bit formats such as MXFP8. Extensive experiments on LLaMA and Qwen models demonstrate that ARCQuant achieves state-of-the-art accuracy, comparable to full-precision baselines in perplexity and downstream tasks. Furthermore, deployment on RTX 5090 and RTX PRO 6000 GPUs confirms practical benefits, achieving up to 3x speedup over FP16. Our code is available at https://github.com/actypedef/ARCQuant.

---

### Task Prototype-Based Knowledge Retrieval for Multi-Task Learning from Partially Annotated Data

Authors: Youngmin Oh, Hyung-Il Kim, Jung Uk Kim
Published: 2026-01-12
Categories: cs.LG, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2601.07474v1

Multi-task learning (MTL) is critical in real-world applications such as autonomous driving and robotics, enabling simultaneous handling of diverse tasks. However, obtaining fully annotated data for all tasks is impractical due to labeling costs. Existing methods for partially labeled MTL typically rely on predictions from unlabeled tasks, making it difficult to establish reliable task associations and potentially leading to negative transfer and suboptimal performance. To address these issues, we propose a prototype-based knowledge retrieval framework that achieves robust MTL instead of relying on predictions from unlabeled tasks. Our framework consists of two key components: (1) a task prototype embedding task-specific characteristics and quantifying task associations, and (2) a knowledge retrieval transformer that adaptively refines feature representations based on these associations. To achieve this, we introduce an association knowledge generating (AKG) loss to ensure the task prototype consistently captures task-specific characteristics. Extensive experiments demonstrate the effectiveness of our framework, highlighting its potential for robust multi-task learning, even when only a subset of tasks is annotated.

---

### AntiPaSTO: Self-Supervised Honesty Steering via Anti-Parallel Representations

Authors: Michael J. Clark
Published: 2026-01-12
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.07473v5

As models grow more capable, humans cannot reliably verify what they say. Scalable steering requires methods that are internal, self-supervised, and transfer out-of-distribution; existing methods satisfy some but not all three. We introduce AntiPaSTO, which separates representations along an antiparallel axis (+1/-1 produce opposite shifts), with coherence constraints preventing collapse. Training uses only two contrasting words inserted into template sentences, with no preference labels. When we use 800 such synthetic pairs on Gemma-3-1B, AntiPaSTO beats prompting baselines by 6.9x Steering F1 on DailyDilemmas and wins on 5 of 6 tested value axes. We also find preliminary evidence that it maintains bidirectional control where prompting triggers refusal.

---

### Learning How to Remember: A Meta-Cognitive Management Method for Structured and Transferable Agent Memory

Authors: Sirui Liang, Pengfei Cao, Jian Zhao, Wenhao Teng, Xiangwen Liao, Jun Zhao, Kang Liu
Published: 2026-01-12
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.07470v1

Large language model (LLM) agents increasingly rely on accumulated memory to solve long-horizon decision-making tasks. However, most existing approaches store memory in fixed representations and reuse it at a single or implicit level of abstraction, which limits generalization and often leads to negative transfer when distribution shift. This paper proposes the Meta-Cognitive Memory Abstraction method (MCMA), which treats memory abstraction as a learnable cognitive skill rather than a fixed design choice. MCMA decouples task execution from memory management by combining a frozen task model with a learned memory copilot. The memory copilot is trained using direct preference optimization, it determines how memories should be structured, abstracted, and reused. Memories are further organized into a hierarchy of abstraction levels, enabling selective reuse based on task similarity. When no memory is transferable, MCMA transfers the ability to abstract and manage memory by transferring the memory copilot. Experiments on ALFWorld, ScienceWorld, and BabyAI demonstrate substantial improvements in performance, out-of-distribution generalization, and cross-task transfer over several baselines.

---

### Knowledge Distillation for LLM-Based Human Activity Recognition in Homes

Authors: Julien Cumin, Oussama Er-Rahmany, Xi Chen
Published: 2026-01-12
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.07469v1

Human Activity Recognition (HAR) is a central problem for context-aware applications, especially for smart homes and assisted living. A few very recent studies have shown that Large Language Models (LLMs) can be used for HAR at home, reaching high performance and addressing key challenges. In this paper, we provide new experimental results regarding the use of LLMs for HAR, on two state-of-the-art datasets. More specifically, we show how recognition performance evolves depending on the size of the LLM used. Moreover, we experiment on the use of knowledge distillation techniques to fine-tune smaller LLMs with HAR reasoning examples generated by larger LLMs. We show that such fine-tuned models can perform almost as well as the largest LLMs, while having 50 times less parameters.

---

### Beyond Dialogue Time: Temporal Semantic Memory for Personalized LLM Agents

Authors: Miao Su, Yucan Guo, Zhongni Hou, Long Bai, Zixuan Li, Yufei Zhang, Guojun Yin, Wei Lin, Xiaolong Jin, Jiafeng Guo, Xueqi Cheng
Published: 2026-01-12
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.07468v2

Memory enables Large Language Model (LLM) agents to perceive, store, and use information from past dialogues, which is essential for personalization. However, existing methods fail to properly model the temporal dimension of memory in two aspects: 1) Temporal inaccuracy: memories are organized by dialogue time rather than their actual occurrence time; 2) Temporal fragmentation: existing methods focus on point-wise memory, losing durative information that captures persistent states and evolving patterns. To address these limitations, we propose Temporal Semantic Memory (TSM), a memory framework that models semantic time for point-wise memory and supports the construction and utilization of durative memory. During memory construction, it first builds a semantic timeline rather than a dialogue one. Then, it consolidates temporally continuous and semantically related information into a durative memory. During memory utilization, it incorporates the query's temporal intent on the semantic timeline, enabling the retrieval of temporally appropriate durative memories and providing time-valid, duration-consistent context to support response generation. Experiments on LongMemEval and LoCoMo show that TSM consistently outperforms existing methods and achieves up to 12.2% absolute improvement in accuracy, demonstrating the effectiveness of the proposed method.

---

### IFDNS: An Iterative Feedback-Driven Neuro-Symbolic Method for Faithful Logical Reasoning

Authors: Xiaoheng Wang, Tongxuan Liu, Zi Gong, Xianzhe Dong, Yuting Zeng, Minhan Hu, Weizhe Huang, Jing Li
Published: 2026-01-12
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.07464v1

Large language models (LLMs) have demonstrated impressive capabilities across a wide range of reasoning tasks, including logical and mathematical problem-solving. While prompt-based methods like Chain-of-Thought (CoT) can enhance LLM reasoning abilities to some extent, they often suffer from a lack of faithfulness, where the derived conclusions may not align with the generated reasoning chain. To address this issue, researchers have explored neuro-symbolic approaches to bolster LLM logical reasoning capabilities. However, existing neuro-symbolic methods still face challenges with information loss during the process. To overcome these limitations, we introduce Iterative Feedback-Driven Neuro-Symbolic (IFDNS), a novel prompt-based method that employs a multi-round feedback mechanism to address LLM limitations in handling complex logical relationships. IFDNS utilizes iterative feedback during the logic extraction phase to accurately extract causal relationship statements and translate them into propositional and logical implication expressions, effectively mitigating information loss issues. Furthermore, IFDNS is orthogonal to existing prompt methods, allowing for seamless integration with various prompting approaches. Empirical evaluations across six datasets demonstrate the effectiveness of IFDNS in significantly improving the performance of CoT and Chain-of-Thought with Self-Consistency (CoT-SC). Specifically, IFDNS achieves a +9.40% accuracy boost for CoT on the LogiQA dataset and a +11.70% improvement for CoT-SC on the PrOntoQA dataset.

---

### Puzzle it Out: Local-to-Global World Model for Offline Multi-Agent Reinforcement Learning

Authors: Sijia Li, Xinran Li, Shibo Chen, Jun Zhang
Published: 2026-01-12
Categories: cs.AI, cs.GT, cs.LG
arXiv: https://arxiv.org/abs/2601.07463v2

Offline multi-agent reinforcement learning (MARL) aims to solve cooperative decision-making problems in multi-agent systems using pre-collected datasets. Existing offline MARL methods primarily constrain training within the dataset distribution, resulting in overly conservative policies that struggle to generalize beyond the support of the data. While model-based approaches offer a promising solution by expanding the original dataset with synthetic data generated from a learned world model, the high dimensionality, non-stationarity, and complexity of multi-agent systems make it challenging to accurately estimate the transitions and reward functions in offline MARL. Given the difficulty of directly modeling joint dynamics, we propose a local-to-global (LOGO) world model, a novel framework that leverages local predictions-which are easier to estimate-to infer global state dynamics, thus improving prediction accuracy while implicitly capturing agent-wise dependencies. Using the trained world model, we generate synthetic data to augment the original dataset, expanding the effective state-action space. To ensure reliable policy learning, we further introduce an uncertainty-aware sampling mechanism that adaptively weights synthetic data by prediction uncertainty, reducing approximation error propagation to policies. In contrast to conventional ensemble-based methods, our approach requires only an additional encoder for uncertainty estimation, significantly reducing computational overhead while maintaining accuracy. Extensive experiments across 8 scenarios against 8 baselines demonstrate that our method surpasses state-of-the-art baselines on standard offline MARL benchmarks, establishing a new model-based baseline for generalizable offline multi-agent learning.

---

### From Sketch to Fresco: Efficient Diffusion Transformer with Progressive Resolution

Authors: Shikang Zheng, Guantao Chen, Lixuan He, Jiacheng Liu, Yuqi Lin, Chang Zou, Linfeng Zhang
Published: 2026-01-12
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.07462v1

Diffusion Transformers achieve impressive generative quality but remain computationally expensive due to iterative sampling. Recently, dynamic resolution sampling has emerged as a promising acceleration technique by reducing the resolution of early sampling steps. However, existing methods rely on heuristic re-noising at every resolution transition, injecting noise that breaks cross-stage consistency and forces the model to relearn global structure. In addition, these methods indiscriminately upsample the entire latent space at once without checking which regions have actually converged, causing accumulated errors, and visible artifacts. Therefore, we propose \textbf{Fresco}, a dynamic resolution framework that unifies re-noise and global structure across stages with progressive upsampling, preserving both the efficiency of low-resolution drafting and the fidelity of high-resolution refinement, with all stages aligned toward the same final target. Fresco achieves near-lossless acceleration across diverse domains and models, including 10$\times$ speedup on FLUX, and 5$\times$ on HunyuanVideo, while remaining orthogonal to distillation, quantization and feature caching, reaching 22$\times$ speedup when combined with distilled models. Our code is in supplementary material and will be released on Github.

---

### Improving Video Question Answering through query-based frame selection

Authors: Himanshu Patil, Geo Jolly, Ramana Raja Buddala, Ganesh Ramakrishnan, Rohit Saluja
Published: 2026-01-12
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2601.07459v1

Video Question Answering (VideoQA) models enhance understanding and interaction with audiovisual content, making it more accessible, searchable, and useful for a wide range of fields such as education, surveillance, entertainment, and content creation. Due to heavy compute requirements, most large visual language models (VLMs) for VideoQA rely on a fixed number of frames by uniformly sampling the video. However, this process does not pick important frames or capture the context of the video. We present a novel query-based selection of frames relevant to the questions based on the submodular mutual Information (SMI) functions. By replacing uniform frame sampling with query-based selection, our method ensures that the chosen frames provide complementary and essential visual information for accurate VideoQA. We evaluate our approach on the MVBench dataset, which spans a diverse set of multi-action video tasks. VideoQA accuracy on this dataset was assessed using two VLMs, namely Video-LLaVA and LLaVA-NeXT, both of which originally employed uniform frame sampling. Experiments were conducted using both uniform and query-based sampling strategies. An accuracy improvement of up to \textbf{4\%} was observed when using query-based frame selection over uniform sampling. Qualitative analysis further highlights that query-based selection, using SMI functions, consistently picks frames better aligned with the question. We opine that such query-based frame selection can enhance accuracy in a wide range of tasks that rely on only a subset of video frames.

---

### RLPO: Residual Listwise Preference Optimization for Long-Context Review Ranking

Authors: Hao Jiang, Zhi Yang, Annan Wang, Yichi Zhang, Weisi Lin
Published: 2026-01-12
Categories: cs.IR, cs.AI
arXiv: https://arxiv.org/abs/2601.07449v2

Review ranking is pivotal in e-commerce for prioritizing diagnostic and authentic feedback from the deluge of user-generated content. While large language models have improved semantic assessment, existing ranking paradigms face a persistent trade-off in long-context settings. Pointwise scoring is efficient but often fails to account for list-level interactions, leading to miscalibrated top-$k$ rankings. Listwise approaches can leverage global context, yet they are computationally expensive and become unstable as candidate lists grow. To address this, we propose Residual Listwise Preference Optimization (RLPO), which formulates ranking as listwise representation-level residual correction over a strong pointwise LLM scorer. RLPO first produces calibrated pointwise scores and item representations, then applies a lightweight encoder over the representations to predict listwise score residuals, avoiding full token-level listwise processing. We also introduce a large-scale benchmark for long-context review ranking with human verification. Experiments show RLPO improves NDCG@k over strong pointwise and listwise baselines and remains robust as list length increases.

---

### PanoSAMic: Panoramic Image Segmentation from SAM Feature Encoding and Dual View Fusion

Authors: Mahdi Chamseddine, Didier Stricker, Jason Rambach
Published: 2026-01-12
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.07447v3

Existing image foundation models are not optimized for spherical images having been trained primarily on perspective images. PanoSAMic integrates the pre-trained Segment Anything (SAM) encoder to make use of its extensive training and integrate it into a semantic segmentation model for panoramic images using multiple modalities. We modify the SAM encoder to output multi-stage features and introduce a novel spatio-modal fusion module that allows the model to select the relevant modalities and best features from each modality for different areas of the input. Furthermore, our semantic decoder uses spherical attention and dual view fusion to overcome the distortions and edge discontinuity often associated with panoramic images. PanoSAMic achieves state-of-the-art (SotA) results on Stanford2D3DS for RGB, RGB-D, and RGB-D-N modalities and on Matterport3D for RGB and RGB-D modalities. https://github.com/dfki-av/PanoSAMic

---

### Surrogate-based Optimization via Clustering for Box-Constrained Problems

Authors: Maaz Ahmad, Iftekhar A. Karimi
Published: 2026-01-12
Categories: cs.LG, math.OC
arXiv: https://arxiv.org/abs/2601.07442v1

Global optimization of large-scale, complex systems such as multi-physics black-box simulations and real-world industrial systems is important but challenging. This work presents a novel Surrogate-Based Optimization framework based on Clustering, SBOC for global optimization of such systems, which can be used with any surrogate modeling technique. At each iteration, it uses a single surrogate model for the entire domain, employs k-means clustering to identify unexplored domain, and exploits a local region around the surrogate optimum to potentially add three new sample points in the domain. SBOC has been tested against sixteen promising benchmarking algorithms using 52 analytical test functions of varying input dimensionalities and shape profiles. It successfully identified a global minimum for most test functions with substantially lower computational effort than other algorithms. It worked especially well on test functions with four or more input variables. It was also among the top six algorithms in approaching a global minimum closely. Overall, SBOC is a robust, reliable, and efficient algorithm for global optimization of box-constrained systems.

---

### Variational Autoencoder with Normalizing flow for X-ray spectral fitting

Authors: Fiona Redmen, Ethan Tregidga, James F. Steiner, Cecilia Garraffo
Published: 2026-01-12
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.07440v1

Black hole X-ray binaries (BHBs) can be studied with spectral fitting to provide physical constraints on accretion in extreme gravitational environments. Traditional methods of spectral fitting such as Markov Chain Monte Carlo (MCMC) face limitations due to computational times. We introduce a probabilistic model, utilizing a variational autoencoder with a normalizing flow, trained to adopt a physical latent space. This neural network produces predictions for spectral-model parameters as well as their full probability distributions. Our implementations result in a significant improvement in spectral reconstructions over a previous deterministic model while performing three orders of magnitude faster than traditional methods.

---

### PIDT: Physics-Informed Digital Twin for Optical Fiber Parameter Estimation

Authors: Zicong Jiang, Magnus Karlsson, Erik Agrell, Christian Häger
Published: 2026-01-12
Categories: eess.SP, cs.LG, physics.optics
arXiv: https://arxiv.org/abs/2601.07436v1

We propose physics-informed digital twin (PIDT): a fiber parameter estimation approach that combines a parameterized split-step method with a physics-informed loss. PIDT improves accuracy and convergence speed with lower complexity compared to previous neural operators.

---

### KALE: Enhancing Knowledge Manipulation in Large Language Models via Knowledge-aware Learning

Authors: Qitan Lv, Tianyu Liu, Qiaosheng Zhang, Xingcheng Xu, Chaochao Lu
Published: 2026-01-12
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2601.07430v1

Despite the impressive performance of large language models (LLMs) pretrained on vast knowledge corpora, advancing their knowledge manipulation-the ability to effectively recall, reason, and transfer relevant knowledge-remains challenging. Existing methods mainly leverage Supervised Fine-Tuning (SFT) on labeled datasets to enhance LLMs' knowledge manipulation ability. However, we observe that SFT models still exhibit the known&incorrect phenomenon, where they explicitly possess relevant knowledge for a given question but fail to leverage it for correct answers. To address this challenge, we propose KALE (Knowledge-Aware LEarning)-a post-training framework that leverages knowledge graphs (KGs) to generate high-quality rationales and enhance LLMs' knowledge manipulation ability. Specifically, KALE first introduces a Knowledge-Induced (KI) data synthesis method that efficiently extracts multi-hop reasoning paths from KGs to generate high-quality rationales for question-answer pairs. Then, KALE employs a Knowledge-Aware (KA) fine-tuning paradigm that enhances knowledge manipulation by internalizing rationale-guided reasoning through minimizing the KL divergence between predictions with and without rationales. Extensive experiments on eight popular benchmarks across six different LLMs demonstrate the effectiveness of KALE, achieving accuracy improvements of up to 11.72% and an average of 4.18%.

---

### SAD: A Large-Scale Strategic Argumentative Dialogue Dataset

Authors: Yongkang Liu, Jiayang Yu, Mingyang Wang, Yiqun Zhang, Ercong Nie, Shi Feng, Daling Wang, Kaisong Song, Hinrich Schütze
Published: 2026-01-12
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.07423v1

Argumentation generation has attracted substantial research interest due to its central role in human reasoning and decision-making. However, most existing argumentative corpora focus on non-interactive, single-turn settings, either generating arguments from a given topic or refuting an existing argument. In practice, however, argumentation is often realized as multi-turn dialogue, where speakers defend their stances and employ diverse argumentative strategies to strengthen persuasiveness. To support deeper modeling of argumentation dialogue, we present the first large-scale \textbf{S}trategic \textbf{A}rgumentative \textbf{D}ialogue dataset, SAD, consisting of 392,822 examples. Grounded in argumentation theories, we annotate each utterance with five strategy types, allowing multiple strategies per utterance. Unlike prior datasets, SAD requires models to generate contextually appropriate arguments conditioned on the dialogue history, a specified stance on the topic, and targeted argumentation strategies. We further benchmark a range of pretrained generative models on SAD and present in-depth analysis of strategy usage patterns in argumentation.

---

### Two Pathways to Truthfulness: On the Intrinsic Encoding of LLM Hallucinations

Authors: Wen Luo, Guangyue Peng, Wei Li, Shaohang Wei, Feifan Song, Liang Wang, Nan Yang, Xingxing Zhang, Jing Jin, Furu Wei, Houfeng Wang
Published: 2026-01-12
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2601.07422v2

Despite their impressive capabilities, large language models (LLMs) frequently generate hallucinations. Previous work shows that their internal states encode rich signals of truthfulness, yet the origins and mechanisms of these signals remain unclear. In this paper, we demonstrate that truthfulness cues arise from two distinct information pathways: (1) a Question-Anchored pathway that depends on question-answer information flow, and (2) an Answer-Anchored pathway that derives self-contained evidence from the generated answer itself. First, we validate and disentangle these pathways through attention knockout and token patching. Afterwards, we uncover notable and intriguing properties of these two mechanisms. Further experiments reveal that (1) the two mechanisms are closely associated with LLM knowledge boundaries; and (2) internal representations are aware of their distinctions. Finally, building on these insightful findings, two applications are proposed to enhance hallucination detection performance. Overall, our work provides new insight into how LLMs internally encode truthfulness, offering directions for more reliable and self-aware generative systems.

---

### Position: Don't be Afraid of Over-Smoothing And Over-Squashing

Authors: Niklas Kormann, Benjamin Doerr, Johannes F. Lutzeyer
Published: 2026-01-12
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2601.07419v1

Over-smoothing and over-squashing have been extensively studied in the literature on Graph Neural Networks (GNNs) over the past years. We challenge this prevailing focus in GNN research, arguing that these phenomena are less critical for practical applications than assumed. We suggest that performance decreases often stem from uninformative receptive fields rather than over-smoothing. We support this position with extensive experiments on several standard benchmark datasets, demonstrating that accuracy and over-smoothing are mostly uncorrelated and that optimal model depths remain small even with mitigation techniques, thus highlighting the negligible role of over-smoothing. Similarly, we challenge that over-squashing is always detrimental in practical applications. Instead, we posit that the distribution of relevant information over the graph frequently factorises and is often localised within a small k-hop neighbourhood, questioning the necessity of jointly observing entire receptive fields or engaging in an extensive search for long-range interactions. The results of our experiments show that architectural interventions designed to mitigate over-squashing fail to yield significant performance gains. This position paper advocates for a paradigm shift in theoretical research, urging a diligent analysis of learning tasks and datasets using statistics that measure the underlying distribution of label-relevant information to better understand their localisation and factorisation.

---

### SDHSI-Net: Learning Better Representations for Hyperspectral Images via Self-Distillation

Authors: Prachet Dev Singh, Shyamsundar Paramasivam, Sneha Barman, Mainak Singha, Ankit Jha, Girish Mishra, Biplab Banerjee
Published: 2026-01-12
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.07416v1

Hyperspectral image (HSI) classification presents unique challenges due to its high spectral dimensionality and limited labeled data. Traditional deep learning models often suffer from overfitting and high computational costs. Self-distillation (SD), a variant of knowledge distillation where a network learns from its own predictions, has recently emerged as a promising strategy to enhance model performance without requiring external teacher networks. In this work, we explore the application of SD to HSI by treating earlier outputs as soft targets, thereby enforcing consistency between intermediate and final predictions. This process improves intra-class compactness and inter-class separability in the learned feature space. Our approach is validated on two benchmark HSI datasets and demonstrates significant improvements in classification accuracy and robustness, highlighting the effectiveness of SD for spectral-spatial learning. Codes are available at https://github.com/Prachet-Dev-Singh/SDHSI.

---

### PLANET v2.0: A comprehensive Protein-Ligand Affinity Prediction Model Based on Mixture Density Network

Authors: Haotian Gao, Xiangying Zhang, Jingyuan Li, Xinchong Chen, Haojie Wang, Yifei Qi, Renxiao Wang
Published: 2026-01-12
Categories: cs.LG, q-bio.MN
arXiv: https://arxiv.org/abs/2601.07415v1

Drug discovery represents a time-consuming and financially intensive process, and virtual screening can accelerate it. Scoring functions, as one of the tools guiding virtual screening, have their precision closely tied to screening efficiency. In our previous study, we developed a graph neural network model called PLANET (Protein-Ligand Affinity prediction NETwork), but it suffers from the defect in representing protein-ligand contact maps. Incorrect binding modes inevitably lead to poor affinity predictions, so accurate prediction of the protein-ligand contact map is desired to improve PLANET. In this study, we have proposed PLANET v2.0 as an upgraded version. The model is trained via multi-objective training strategy and incorporates the Mixture Density Network to predict binding modes. Except for the probability density distributions of non-covalent interactions, we innovatively employ another Gaussian mixture model to describe the relationship between distance and energy of each interaction pair and predict protein-ligand affinity like calculating the mathematical expectation. As on the CASF-2016 benchmark, PLANET v2.0 demonstrates excellent scoring power, ranking power, and docking power. The screening power of PLANET v2.0 gets notably improved compared to PLANET and Glide SP and it demonstrates robust validation on a commercial ultra-large-scale dataset. Given its efficiency and accuracy, PLANET v2.0 can hopefully become one of the practical tools for virtual screening workflows. PLANET v2.0 is freely available at https://www.pdbbind-plus.org.cn/planetv2.

---