# Research Papers — 2026-01 · bundle page 133 of 189

> Full-text markdown of papers #6601–6650 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/133
[← Previous bundle](https://aipod.dev/papers/archive/2026-01/page/132.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-01/page/134.md)

### NOVAK: Unified adaptive optimizer for deep neural networks

Authors: Sergii Kavun
Published: 2026-01-11
Categories: cs.LG, cs.AI, math.OC
arXiv: https://arxiv.org/abs/2601.07876v1

This work introduces NOVAK, a modular gradient-based optimization algorithm that integrates adaptive moment estimation, rectified learning-rate scheduling, decoupled weight regularization, multiple variants of Nesterov momentum, and lookahead synchronization into a unified, performance-oriented framework. NOVAK adopts a dual-mode architecture consisting of a streamlined fast path designed for production. The optimizer employs custom CUDA kernels that deliver substantial speedups (3-5 for critical operations) while preserving numerical stability under standard stochastic-optimization assumptions. We provide fully developed mathematical formulations for rectified adaptive learning rates, a memory-efficient lookahead mechanism that reduces overhead from O(2p) to O(p + p/k), and the synergistic coupling of complementary optimization components. Theoretical analysis establishes convergence guarantees and elucidates the stability and variance-reduction properties of the method. Extensive empirical evaluation on CIFAR-10, CIFAR-100, ImageNet, and ImageNette demonstrates NOVAK superiority over 14 contemporary optimizers, including Adam, AdamW, RAdam, Lion, and Adan. Across architectures such as ResNet-50, VGG-16, and ViT, NOVAK consistently achieves state-of-the-art accuracy, and exceptional robustness, attaining very high accuracy on VGG-16/ImageNette demonstrating superior architectural robustness compared to contemporary optimizers. The results highlight that NOVAKs architectural contributions (particularly rectification, decoupled decay, and hybrid momentum) are crucial for reliable training of deep plain networks lacking skip connections, addressing a long-standing limitation of existing adaptive optimization methods.

---

### Multiplicative Orthogonal Sequential Editing for Language Models

Authors: Hao-Xiang Xu, Jun-Yu Ma, Ziqi Peng, Yuhao Sun, Zhen-Hua Ling, Jia-Chen Gu
Published: 2026-01-11
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.07873v1

Knowledge editing aims to efficiently modify the internal knowledge of large language models (LLMs) without compromising their other capabilities. The prevailing editing paradigm, which appends an update matrix to the original parameter matrix, has been shown by some studies to damage key numerical stability indicators (such as condition number and norm), thereby reducing editing performance and general abilities, especially in sequential editing scenario. Although subsequent methods have made some improvements, they remain within the additive framework and have not fundamentally addressed this limitation. To solve this problem, we analyze it from both statistical and mathematical perspectives and conclude that multiplying the original matrix by an orthogonal matrix does not change the numerical stability of the matrix. Inspired by this, different from the previous additive editing paradigm, a multiplicative editing paradigm termed Multiplicative Orthogonal Sequential Editing (MOSE) is proposed. Specifically, we first derive the matrix update in the multiplicative form, the new knowledge is then incorporated into an orthogonal matrix, which is multiplied by the original parameter matrix. In this way, the numerical stability of the edited matrix is unchanged, thereby maintaining editing performance and general abilities. We compared MOSE with several current knowledge editing methods, systematically evaluating their impact on both editing performance and the general abilities across three different LLMs. Experimental results show that MOSE effectively limits deviations in the edited parameter matrix and maintains its numerical stability. Compared to current methods, MOSE achieves a 12.08% improvement in sequential editing performance, while retaining 95.73% of general abilities across downstream tasks. The code is available at https://github.com/famoustourist/MOSE.

---

### Robust Bayesian Optimization via Tempered Posteriors

Authors: Jiguang Li, Hengrui Luo
Published: 2026-01-11
Categories: stat.ME, cs.LG
arXiv: https://arxiv.org/abs/2601.07094v2

Bayesian optimization (BO) iteratively fits a Gaussian process (GP) surrogate to accumulated evaluations and selects new queries via an acquisition function. Under local misspecification, this feedback loop can produce overconfidence precisely in the region guiding subsequent decisions. We develop a tempered GP-based BO framework that raises the likelihood to a power $α\in(0,1)$. For a generalized family of improvement acquisitions indexed by $g$, including probability of improvement (PI, $g=0$) and expected improvement (EI, $g=1$), we derive finite-time cumulative regret bounds with adaptively learned kernel hyperparameters. The analysis shows that tempering reduces the noise-driven confidence and information-gain contributions to regret, while a deterministic RKHS term prevents arbitrarily aggressive tempering from being uniformly beneficial. It also clarifies the role of the acquisition function: positive-order $g$-EI rules preserve the usual information-gain regret behavior, whereas zero-jitter PI is more exploitative and admits a weaker worst-case guarantee. Motivated by our theoretic findings, we propose a prequential procedure for selecting $α$ online: it decreases $α$ when realized prediction errors exceed model-implied uncertainty and returns $α$ toward one as calibration improves. Empirical results demonstrate that tempering provides a practical yet theoretically grounded tool for stabilizing BO surrogates under localized sampling.

---

### 3D Wavelet-Based Structural Priors for Controlled Diffusion in Whole-Body Low-Dose PET Denoising

Authors: Peiyuan Jing, Yue Yang, Chun-Wun Cheng, Zhenxuan Zhang, Liutao Yang, Thiago V. Lima, Klaus Strobel, Antoine Leimgruber, Angelica Aviles-Rivero, Guang Yang, Javier A. Montoya-Zegarra
Published: 2026-01-11
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2601.07093v4

Low-dose Positron Emission Tomography (PET) imaging reduces patient radiation exposure but suffers from increased noise that degrades image quality and diagnostic reliability. Although diffusion models have demonstrated strong denoising capability, their stochastic nature makes it challenging to enforce anatomically consistent structures, particularly in low signal-to-noise regimes and volumetric whole-body imaging. We propose Wavelet-Conditioned ControlNet (WCC-Net), a fully 3D diffusion-based framework that introduces explicit frequency-domain structural priors via wavelet representations to guide volumetric PET denoising. By injecting wavelet-based structural guidance into a frozen pretrained diffusion backbone through a lightweight control branch, WCC-Net decouples anatomical structure from noise while preserving generative expressiveness and 3D structural continuity. Extensive experiments demonstrate that WCC-Net consistently outperforms CNN-, GAN-, and diffusion-based baselines. On the internal 1/20-dose test set, WCC-Net improves PSNR by +1.21 dB and SSIM by +0.008 over a strong diffusion baseline, while reducing structural distortion (GMSD) and intensity error (NMAE). Moreover, WCC-Net generalizes robustly to unseen dose levels (1/50 and 1/4), achieving superior quantitative performance and improved volumetric anatomical consistency.

---

### Efficient Visual Question Answering Pipeline for Autonomous Driving via Scene Region Compression

Authors: Yuliang Cai, Dongqiangzi Ye, Zitian Chen, Chongruo Wu
Published: 2026-01-11
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.07092v1

Autonomous driving increasingly relies on Visual Question Answering (VQA) to enable vehicles to understand complex surroundings by analyzing visual inputs and textual queries. Currently, a paramount concern for VQA in this domain is the stringent requirement for fast latency and real-time processing, as delays directly impact real-world safety in this safety-critical application. However, current state-of-the-art VQA models, particularly large vision-language models (VLMs), often prioritize performance over computational efficiency. These models typically process dense patch tokens for every frame, leading to prohibitive computational costs (FLOPs) and significant inference latency, especially with long video sequences. This focus limits their practical deployment in real-time autonomous driving scenarios. To tackle this issue, we propose an efficient VLM framework for autonomous driving VQA tasks, SRC-Pipeline. It learns to compress early frame tokens into a small number of high-level tokens while retaining full patch tokens for recent frames. Experiments on autonomous driving video question answering tasks show that our approach achieves 66% FLOPs reduction while maintaining comparable performance, enabling VLMs to operate more effectively in real-time, safety-critical autonomous driving settings.

---

### When Should We Introduce Safety Interventions During Pretraining?

Authors: Dylan Sam, Sachin Goyal, Pratyush Maini, Alexander Robey, J. Zico Kolter
Published: 2026-01-11
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.07087v2

Prior work has shown that safety interventions applied during pretraining, such as removing and rephrasing harmful content, can substantially improve the robustness of the resulting models. In this paper, we study the fundamental question that prior work has overlooked: "When during pretraining should safety interventions be introduced?" We keep the underlying data sources and pretraining interventions fixed, varying the intervention start time (after 0%, 20%, or 60% of pretraining tokens). We find that the optimal start time is not one-size-fits-all: with standard top-k decoding, introducing interventions after a short initial phase of safe-only pretraining (20%-60%) often yields the strongest robustness, with the clearest benefits emerging after downstream, benign finetuning. In contrast, for safety-aware inference, interventions starting from the beginning improve steerability towards safer generations. Finally, we observe that earlier interventions reshape internal representations: linear probes more cleanly separate safe vs harmful examples. Our results are the first to establish intervention timing as a key curriculum design choice for safety.

---

### XBTorch: A Unified Framework for Modeling and Co-Design of Crossbar-Based Deep Learning Accelerators

Authors: Osama Yousuf, Andreu L. Glasmann, Martin Lueker-Boden, Sina Najmaei, Gina C. Adam
Published: 2026-01-11
Categories: cs.ET, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2601.07086v1

Emerging memory technologies have gained significant attention as a promising pathway to overcome the limitations of conventional computing architectures in deep learning applications. By enabling computation directly within memory, these technologies - built on nanoscale devices with tunable and nonvolatile conductance - offer the potential to drastically reduce energy consumption and latency compared to traditional von Neumann systems. This paper introduces XBTorch (short for CrossBarTorch), a novel simulation framework that integrates seamlessly with PyTorch and provides specialized tools for accurately and efficiently modeling crossbar-based systems based on emerging memory technologies. Through detailed comparisons and case studies involving hardware-aware training and inference, we demonstrate how XBTorch offers a unified interface for key research areas such as device-level modeling, cross-layer co-design, and inference-time fault tolerance. While exemplar studies utilize ferroelectric field-effect transistor (FeFET) models, the framework remains technology-agnostic - supporting other emerging memories such as resistive RAM (ReRAM), as well as enabling user-defined custom device models. The code is publicly available at: https://github.com/ADAM-Lab-GW/xbtorch

---

### The AI Cognitive Trojan Horse: How Large Language Models May Bypass Human Epistemic Vigilance

Authors: Andrew D. Maynard
Published: 2026-01-11
Categories: cs.HC, cs.AI, cs.CY
arXiv: https://arxiv.org/abs/2601.07085v2

Large language model (LLM)-based conversational AI systems present a challenge to human cognition that current frameworks for understanding misinformation and persuasion do not adequately address. This paper proposes that a significant epistemic risk from conversational AI may lie not in inaccuracy or intentional deception, but in something more fundamental: these systems may be configured, through optimization processes that make them useful, to present characteristics that bypass the cognitive mechanisms humans evolved to evaluate incoming information. The Cognitive Trojan Horse hypothesis draws on Sperber and colleagues' theory of epistemic vigilance -- the parallel cognitive process monitoring communicated information for reasons to doubt -- and proposes that LLM-based systems present 'honest non-signals': genuine characteristics (fluency, helpfulness, apparent disinterest) that fail to carry the information equivalent human characteristics would carry, because in humans these are costly to produce while in LLMs they are computationally trivial. Four mechanisms of potential bypass are identified: processing fluency decoupled from understanding, trust-competence presentation without corresponding stakes, cognitive offloading that delegates evaluation itself to the AI, and optimization dynamics that systematically produce sycophancy. The framework generates testable predictions, including a counterintuitive speculation that cognitively sophisticated users may be more vulnerable to AI-mediated epistemic influence. This reframes AI safety as partly a problem of calibration -- aligning human evaluative responses with the actual epistemic status of AI-generated content -- rather than solely a problem of preventing deception.

---

### Robust Mean Estimation under Quantization

Authors: Pedro Abdalla, Junren Chen
Published: 2026-01-11
Categories: stat.ML, cs.LG, math.ST
arXiv: https://arxiv.org/abs/2601.07074v1

We consider the problem of mean estimation under quantization and adversarial corruption. We construct multivariate robust estimators that are optimal up to logarithmic factors in two different settings. The first is a one-bit setting, where each bit depends only on a single sample, and the second is a partial quantization setting, in which the estimator may use a small fraction of unquantized data.

---

### Billboard in Focus: Estimating Driver Gaze Duration from a Single Image

Authors: Carlos Pizarroso, Zuzana Berger Haladová, Zuzana Černeková, Viktor Kocur
Published: 2026-01-11
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.07073v1

Roadside billboards represent a central element of outdoor advertising, yet their presence may contribute to driver distraction and accident risk. This study introduces a fully automated pipeline for billboard detection and driver gaze duration estimation, aiming to evaluate billboard relevance without reliance on manual annotations or eye-tracking devices. Our pipeline operates in two stages: (1) a YOLO-based object detection model trained on Mapillary Vistas and fine-tuned on BillboardLamac images achieved 94% mAP@50 in the billboard detection task (2) a classifier based on the detected bounding box positions and DINOv2 features. The proposed pipeline enables estimation of billboard driver gaze duration from individual frames. We show that our method is able to achieve 68.1% accuracy on BillboardLamac when considering individual frames. These results are further validated using images collected from Google Street View.

---

### Overcoming the Retrieval Barrier: Indirect Prompt Injection in the Wild for LLM Systems

Authors: Hongyan Chang, Ergute Bao, Xinjian Luo, Ting Yu
Published: 2026-01-11
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2601.07072v1

Large language models (LLMs) increasingly rely on retrieving information from external corpora. This creates a new attack surface: indirect prompt injection (IPI), where hidden instructions are planted in the corpora and hijack model behavior once retrieved. Previous studies have highlighted this risk but often avoid the hardest step: ensuring that malicious content is actually retrieved. In practice, unoptimized IPI is rarely retrieved under natural queries, which leaves its real-world impact unclear. We address this challenge by decomposing the malicious content into a trigger fragment that guarantees retrieval and an attack fragment that encodes arbitrary attack objectives. Based on this idea, we design an efficient and effective black-box attack algorithm that constructs a compact trigger fragment to guarantee retrieval for any attack fragment. Our attack requires only API access to embedding models, is cost-efficient (as little as $0.21 per target user query on OpenAI's embedding models), and achieves near-100% retrieval across 11 benchmarks and 8 embedding models (including both open-source models and proprietary services). Based on this attack, we present the first end-to-end IPI exploits under natural queries and realistic external corpora, spanning both RAG and agentic systems with diverse attack objectives. These results establish IPI as a practical and severe threat: when a user issued a natural query to summarize emails on frequently asked topics, a single poisoned email was sufficient to coerce GPT-4o into exfiltrating SSH keys with over 80% success in a multi-agent workflow. We further evaluate several defenses and find that they are insufficient to prevent the retrieval of malicious text, highlighting retrieval as a critical open vulnerability.

---

### Neuromorphic FPGA Design for Digital Signal Processing

Authors: Justin London
Published: 2026-01-11
Categories: cs.NE, eess.SP
arXiv: https://arxiv.org/abs/2601.07069v1

In this paper, the foundations of neuromorphic computing, spiking neural networks (SNNs) and memristors, are analyzed and discussed. Neuromorphic computing is then applied to FPGA design for digital signal processing (DSP). Finite impulse response (FIR) and infinite impulse response (IIR) filters are implemented with and without neuromorphic computing in Vivado using Verilog HDL. The results suggest that neuromorphic computing can provide low-latency and synaptic plasticity thereby enabling continuous on-chip learning. Due to their parallel and event-driven nature, neuromorphic computing can reduce power consumption by eliminating von Neumann bottlenecks and improve efficiency, but at the cost of reduced numeric precision.

---

### Automated Domain Question Mapping (DQM) with Educational Learning Materials

Authors: Jiho Noh, Mukhesh Raghava Katragadda, Dabae Lee
Published: 2026-01-11
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.07062v1

Concept maps have been widely utilized in education to depict knowledge structures and the interconnections between disciplinary concepts. Nonetheless, devising a computational method for automatically constructing a concept map from unstructured educational materials presents challenges due to the complexity and variability of educational content. We focus primarily on two challenges: (1) the lack of disciplinary concepts that are specifically designed for multi-level pedagogical purposes from low-order to high-order thinking, and (2) the limited availability of labeled data concerning disciplinary concepts and their interrelationships. To tackle these challenges, this research introduces an innovative approach for constructing Domain Question Maps (DQMs), rather than traditional concept maps. By formulating specific questions aligned with learning objectives, DQMs enhance knowledge representation and improve readiness for learner engagement. The findings indicate that the proposed method can effectively generate educational questions and discern hierarchical relationships among them, leading to structured question maps that facilitate personalized and adaptive learning in downstream applications.

---

### Local EGOP for Continuous Index Learning

Authors: Alex Kokot, Anand Hemmady, Vydhourie Thiyageswaran, Marina Meila
Published: 2026-01-11
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2601.07061v4

We introduce the setting of continuous index learning, in which a function of many variables varies only along a small number of directions at each point. For efficient estimation, it is beneficial for a learning algorithm to adapt, near each point $x$, to the subspace that captures the local variability of the function $f$. We pose this task as kernel adaptation along a manifold with noise, and introduce Local EGOP learning, a recursive algorithm that utilizes the Expected Gradient Outer Product (EGOP) quadratic form as both a metric and inverse-covariance of our target distribution. We prove that Local EGOP learning adapts to the regularity of the function of interest, showing that under a supervised noisy manifold hypothesis, intrinsic dimensional learning rates are achieved for arbitrarily high-dimensional noise. Empirically, we compare our algorithm to the feature learning capabilities of deep learning. Additionally, we demonstrate improved regression quality compared to two-layer neural networks in the continuous single-index setting.

---

### Hallucinations Live in Variance

Authors: Aaron R. Flouro, Shawn P. Chadwick
Published: 2026-01-11
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.07058v1

Benchmarks measure whether a model is correct. They do not measure whether a model is reliable. This distinction is largely academic for single-shot inference, but becomes critical for agentic AI systems, where a single rephrased prompt can trigger cascading failures in multi-step execution. Yet this form of instability is not captured by existing evaluations. Hallucinations live in variance: they arise when semantically equivalent prompts activate inconsistent internal pathways, producing divergent outputs. Consistent but incorrect outputs reflect bias or missing knowledge; confident guessing reflects calibration failure. Neither constitutes hallucination under this definition. When error is variance-dominated, reducing redundant pathways improves reliability without adding knowledge. We formalize this through Semantic Stability (SS), measured via Paraphrase Consistency (PC@k): generate k paraphrases, greedy decode each, compute mode agreement. SS is a diagnostic for variance-driven unreliability, not a method for improving correctness. We show that a dense Qwen3-0.6B agrees with itself only 23.8% of the time; at 32% sparsity, agreement jumps to 55.9%. A phase diagram reveals the sweet spot where variance reduction outpaces bias accumulation, and regimes where stability collapses onto wrong answers.

---

### Adversarial Attacks on Medical Hyperspectral Imaging Exploiting Spectral-Spatial Dependencies and Multiscale Features

Authors: Yunrui Gu, Zhenzhe Gao, Cong Kong, Jiawei Du, Zhaoxia Yin
Published: 2026-01-11
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2601.07056v2

Medical hyperspectral imaging (MHSI) has shown strong potential for disease diagnosis by capturing spectral-spatial information of tissues. While deep learning has substantially improved MHSI classification accuracy, its robustness remains limited due to the well-known trade-off between accuracy and robustness in Deep Neural Networks (DNNs). This issue is particularly critical in MHSI, where reliable prediction depends on local tissue relationships and multiscale spectral-spatial structures. A practical way to improve robustness is to identify the most unstable adversarial examples and incorporate them into adversarial training. However, existing attack methods do not sufficiently exploit these MHSI-specific properties, leading to suboptimal attack effectiveness and limited value for robustness enhancement. To address this gap, we propose a structured adversarial attack framework for MHSI that progressively models its local spectral-spatial dependencies and multiscale hierarchical representations. The proposed method generates anatomically consistent perturbations by modeling neighborhood dependencies and hierarchical spectral-spatial features. Experiments on the brain and choledoch datasets show that our method more effectively degrades lesion-related classification performance in critical tumor regions than existing baselines while maintaining low perturbation magnitude. These results reveal a clinically relevant robustness weakness in current MHSI models and provide stronger adversarial samples for developing targeted defense strategies.

---

### Dr. Zero: Self-Evolving Search Agents without Training Data

Authors: Zhenrui Yue, Kartikeya Upasani, Xianjun Yang, Suyu Ge, Shaoliang Nie, Yuning Mao, Zhe Liu, Dong Wang
Published: 2026-01-11
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.07055v2

As high-quality data becomes increasingly difficult to obtain, self-evolution without curated training data has emerged as a promising paradigm. This approach allows large language models (LLMs) to autonomously generate and solve complex problems, thereby improving their reasoning capabilities. However, multi-turn search agents struggle in this setting due to limited question diversity and the substantial compute required for multi-step reasoning and tool use. In this work, we introduce Dr. Zero, a framework that enables search agents to effectively self-evolve without human-annotated training data, relying solely on an external search engine as their knowledge environment. In particular, we design a self-evolution feedback loop where a proposer generates structurally diverse questions to train a solver initialized from the same base model. As the solver evolves, it incentivizes the proposer to produce increasingly difficult yet solvable tasks, thus establishing an automated curriculum to refine both agents. To enhance training efficiency, we also introduce hop-grouped relative policy optimization (HRPO). This method clusters structurally similar questions to construct group-level baselines, effectively minimizing the sampling overhead in evaluating each query's individual difficulty and solvability. Consequently, HRPO significantly reduces the compute requirements for proposer training and reward estimation without compromising performance or stability. Extensive experimental results demonstrate that Dr. Zero matches or surpasses fully supervised search agents on several question answering benchmarks, showing that strong agentic search and evidence-grounded reasoning can emerge solely through self-evolution.

---

### Fine-Tuning vs. RAG for Multi-Hop Question Answering with Novel Knowledge

Authors: Zhuoyi Yang, Yurun Song, Iftekhar Ahmed, Ian Harris
Published: 2026-01-11
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2601.07054v1

Multi-hop question answering is widely used to evaluate the reasoning capabilities of large language models (LLMs), as it requires integrating multiple pieces of supporting knowledge to arrive at a correct answer. While prior work has explored different mechanisms for providing knowledge to LLMs, such as finetuning and retrieval-augmented generation (RAG), their relative effectiveness for multi-hop question answering remains insufficiently understood, particularly when the required knowledge is temporally novel. In this paper, we systematically compare parametric and non-parametric knowledge injection methods for open-domain multi-hop question answering. We evaluate unsupervised fine-tuning (continual pretraining), supervised fine-tuning, and retrieval-augmented generation across three 7B-parameter open-source LLMs. Experiments are conducted on two benchmarks: QASC, a standard multi-hop science question answering dataset, and a newly constructed dataset of over 10,000 multi-hop questions derived from Wikipedia events in 2024, designed to test knowledge beyond the models' pretraining cutoff. Our results show that unsupervised fine-tuning provides only limited gains over base models, suggesting that continual pretraining alone is insufficient for improving multi-hop reasoning accuracy. In contrast, retrieval-augmented generation yields substantial and consistent improvements, particularly when answering questions that rely on temporally novel information. Supervised fine-tuning achieves the highest overall accuracy across models and datasets. These findings highlight fundamental differences in how knowledge injection mechanisms support multi-hop question answering and underscore the importance of retrieval-based methods when external or compositional knowledge is required.

---

### GPU-Accelerated ANNS: Quantized for Speed, Built for Change

Authors: Hunter McCoy, Zikun Wang, Prashant Pandey
Published: 2026-01-11
Categories: cs.DB, cs.AI
arXiv: https://arxiv.org/abs/2601.07048v5

Approximate nearest neighbor search (ANNS) is a core problem in machine learning and information retrieval applications. GPUs offer a promising path to high-performance ANNS: they provide massive parallelism for distance computations, are readily available, and can co-locate with downstream applications. Despite these advantages, current GPU-accelerated ANNS systems face three key limitations. First, real-world applications operate on evolving datasets that require fast batch updates, yet most GPU indices must be rebuilt from scratch when new data arrives. Second, high-dimensional vectors strain memory bandwidth, but current GPU systems lack efficient quantization techniques that reduce data movement without introducing costly random memory accesses. Third, the data-dependent memory accesses inherent to greedy search make overlapping compute and memory difficult, leading to reduced performance. We present Jasper, a GPU-native ANNS system with both high query throughput and updatability. Jasper builds on the Vamana graph index and overcomes existing bottlenecks via three contributions: (1) a CUDA batch-parallel construction algorithm that enables lock-free streaming insertions, (2) a GPU-efficient implementation of RaBitQ quantization that reduces memory footprint up to 8x without the random access penalties, and (3) an optimized greedy search kernel that increases compute utilization, resulting in better latency hiding and higher throughput. Our evaluation across five datasets shows that Jasper achieves up to 1.84x higher query throughput than CAGRA and achieves up to 80% peak utilization as measured by the roofline model. Jasper's construction scales efficiently and constructs indices an average of 7x faster than CAGRA while providing updatability that CAGRA lacks. Compared to BANG, the previous fastest GPU Vamana implementation, Jasper delivers 10-74x faster queries.

---

### Engineering of Hallucination in Generative AI: It's not a Bug, it's a Feature

Authors: Tim Fingscheidt, Patrick Blumenberg, Björn Möller
Published: 2026-01-11
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.07046v1

Generative artificial intelligence (AI) is conquering our lives at lightning speed. Large language models such as ChatGPT answer our questions or write texts for us, large computer vision models such as GAIA-1 generate videos on the basis of text descriptions or continue prompted videos. These neural network models are trained using large amounts of text or video data, strictly according to the real data employed in training. However, there is a surprising observation: When we use these models, they only function satisfactorily when they are allowed a certain degree of fantasy (hallucination). While hallucination usually has a negative connotation in generative AI - after all, ChatGPT is expected to give a fact-based answer! - this article recapitulates some simple means of probability engineering that can be used to encourage generative AI to hallucinate to a limited extent and thus lead to the desired results. We have to ask ourselves: Is hallucination in gen-erative AI probably not a bug, but rather a feature?

---

### When Abundance Conceals Weakness: Knowledge Conflict in Multilingual Models

Authors: Jiaqi Zhao, Qiang Huang, Haodong Chen, Xiaoxing You, Jun Yu
Published: 2026-01-11
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.07041v1

Large Language Models (LLMs) encode vast world knowledge across multiple languages, yet their internal beliefs are often unevenly distributed across linguistic spaces. When external evidence contradicts these language-dependent memories, models encounter \emph{cross-lingual knowledge conflict}, a phenomenon largely unexplored beyond English-centric settings. We introduce \textbf{CLEAR}, a \textbf{C}ross-\textbf{L}ingual knowl\textbf{E}dge conflict ev\textbf{A}luation f\textbf{R}amework that systematically examines how multilingual LLMs reconcile conflicting internal beliefs and multilingual external evidence. CLEAR decomposes conflict resolution into four progressive scenarios, from multilingual parametric elicitation to competitive multi-source cross-lingual induction, and systematically evaluates model behavior across two complementary QA benchmarks with distinct task characteristics. We construct multilingual versions of ConflictQA and ConflictingQA covering 10 typologically diverse languages and evaluate six representative LLMs. Our experiments reveal a task-dependent decision dichotomy. In reasoning-intensive tasks, conflict resolution is dominated by language resource abundance, with high-resource languages exerting stronger persuasive power. In contrast, for entity-centric factual conflicts, linguistic affinity, not resource scale, becomes decisive, allowing low-resource but linguistically aligned languages to outperform distant high-resource ones.

---

### Task Arithmetic with Support Languages for Low-Resource ASR

Authors: Emma Rafkin, Dan DeGenaro, Xiulin Yang
Published: 2026-01-11
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.07038v2

The development of resource-constrained approaches to automatic speech recognition (ASR) is of great interest due to its broad applicability to many low-resource languages for which there is scant usable data. Existing approaches to many low-resource natural language processing tasks leverage additional data from higher-resource languages that are closely related to a target low-resource language. One increasingly popular approach uses task arithmetic to combine models trained on different tasks to create a model for a task where there is little to no training data. In this paper, we consider training on a particular language to be a task, and we generate task vectors by fine-tuning variants of the Whisper ASR system. For pairs of high- and low-resource languages, we merge task vectors via a linear combination which is optimized on the downstream word error rate on the low-resource target language's validation set. Across 23 low-resource target languages for which we evaluate this technique, we find consistent word error rate improvements of up to 10% compared to a baseline without our approach.

---

### Mid-Think: Training-Free Intermediate-Budget Reasoning via Token-Level Triggers

Authors: Wang Yang, Debargha Ganguly, Xinpeng Li, Chaoda Song, Shouren Wang, Vikash Singh, Vipin Chaudhary, Xiaotian Han
Published: 2026-01-11
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2601.07036v2

Hybrid reasoning language models are commonly controlled through high-level Think/No-think instructions to regulate reasoning behavior, yet we found that such mode switching is largely driven by a small set of trigger tokens rather than the instructions themselves. Through attention analysis and controlled prompting experiments, we show that a leading ``Okay'' token induces reasoning behavior, while the newline pattern following ``</think>'' suppresses it. Based on this observation, we propose Mid-Think, a simple training-free prompting format that combines these triggers to achieve intermediate-budget reasoning, consistently outperforming fixed-token and prompt-based baselines in terms of the accuracy-length trade-off. Furthermore, applying Mid-Think to RL training after SFT reduces training time by approximately 15% while improving final performance of Qwen3-8B on AIME from 69.8% to 72.4% and on GPQA from 58.5% to 61.1%, demonstrating its effectiveness for both inference-time control and RL-based reasoning training.

---

### Explainable Deep Radiogenomic Molecular Imaging for MGMT Methylation Prediction in Glioblastoma

Authors: Hasan M Jamil
Published: 2026-01-11
Categories: cs.LG, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2601.07035v1

Glioblastoma (GBM) is a highly aggressive primary brain tumor with limited therapeutic options and poor prognosis. The methylation status of the O6-methylguanine-DNA methyltransferase (MGMT) gene promoter is a critical molecular biomarker that influences patient response to temozolomide chemotherapy. Traditional methods for determining MGMT status rely on invasive biopsies and are limited by intratumoral heterogeneity and procedural risks. This study presents a radiogenomic molecular imaging analysis framework for the non-invasive prediction of MGMT promoter methylation using multi-parametric magnetic resonance imaging (mpMRI). Our approach integrates radiomics, deep learning, and explainable artificial intelligence (XAI) to analyze MRI-derived imaging phenotypes and correlate them with molecular labels. Radiomic features are extracted from FLAIR, T1-weighted, T1-contrast-enhanced, and T2-weighted MRI sequences, while a 3D convolutional neural network learns deep representations from the same modalities. These complementary features are fused using both early fusion and attention-based strategies and classified to predict MGMT methylation status. To enhance clinical interpretability, we apply XAI methods such as Grad-CAM and SHAP to visualize and explain model decisions. The proposed framework is trained on the RSNA-MICCAI Radiogenomic Classification dataset and externally validated on the BraTS 2021 dataset. This work advances the field of molecular imaging by demonstrating the potential of AI-driven radiogenomics for precision oncology, supporting non-invasive, accurate, and interpretable prediction of clinically actionable molecular biomarkers in GBM.

---

### Codified Foreshadowing-Payoff Text Generation

Authors: Longfei Yun, Kun Zhou, Yupeng Hou, Letian Peng, Jingbo Shang
Published: 2026-01-11
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.07033v1

Foreshadowing and payoff are ubiquitous narrative devices through which authors introduce commitments early in a story and resolve them through concrete, observable outcomes. However, despite advances in story generation, large language models (LLMs) frequently fail to bridge these long-range narrative dependencies, often leaving "Chekhov's guns" unfired even when the necessary context is present. Existing evaluations largely overlook this structural failure, focusing on surface-level coherence rather than the logical fulfillment of narrative setups. In this paper, we introduce Codified Foreshadowing-Payoff Generation (CFPG), a novel framework that reframes narrative quality through the lens of payoff realization. Recognizing that LLMs struggle to intuitively grasp the "triggering mechanism" of a foreshadowed event, CFPG transforms narrative continuity into a set of executable causal predicates. By mining and encoding Foreshadow-Trigger-Payoff triples from the BookSum corpus, we provide structured supervision that ensures foreshadowed commitments are not only mentioned but also temporally and logically fulfilled. Experiments demonstrate that CFPG significantly outperforms standard prompting baselines in payoff accuracy and narrative alignment. Our findings suggest that explicitly codifying narrative mechanics is essential for moving LLMs from surface-level fluency to genuine narrative competence.

---

### CloneMem: Benchmarking Long-Term Memory for AI Clones

Authors: Sen Hu, Zhiyu Zhang, Yuxiang Wei, Xueran Han, Zhenheng Tang, Huacan Wang, Ronghao Chen
Published: 2026-01-11
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.07023v1

AI Clones aim to simulate an individual's thoughts and behaviors to enable long-term, personalized interaction, placing stringent demands on memory systems to model experiences, emotions, and opinions over time. Existing memory benchmarks primarily rely on user-agent conversational histories, which are temporally fragmented and insufficient for capturing continuous life trajectories. We introduce CloneMem, a benchmark for evaluating longterm memory in AI Clone scenarios grounded in non-conversational digital traces, including diaries, social media posts, and emails, spanning one to three years. CloneMem adopts a hierarchical data construction framework to ensure longitudinal coherence and defines tasks that assess an agent's ability to track evolving personal states. Experiments show that current memory mechanisms struggle in this setting, highlighting open challenges for life-grounded personalized AI. Code and dataset are available at https://github.com/AvatarMemory/CloneMemBench

---

### Solar Open Technical Report

Authors: Sungrae Park, Sanghoon Kim, Jungho Cho, Gyoungjin Gim, Dawoon Jung, Mikyoung Cha, Eunhae Choo, Taekgyu Hong, Minbyul Jeong, SeHwan Joo, Minsoo Khang, Eunwon Kim et al.
Published: 2026-01-11
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.07022v1

We introduce Solar Open, a 102B-parameter bilingual Mixture-of-Experts language model for underserved languages. Solar Open demonstrates a systematic methodology for building competitive LLMs by addressing three interconnected challenges. First, to train effectively despite data scarcity for underserved languages, we synthesize 4.5T tokens of high-quality, domain-specific, and RL-oriented data. Second, we coordinate this data through a progressive curriculum jointly optimizing composition, quality thresholds, and domain coverage across 20 trillion tokens. Third, to enable reasoning capabilities through scalable RL, we apply our proposed framework SnapPO for efficient optimization. Across benchmarks in English and Korean, Solar Open achieves competitive performance, demonstrating the effectiveness of this methodology for underserved language AI development.

---

### Tight Analysis of Decentralized SGD: A Markov Chain Perspective

Authors: Lucas Versini, Paul Mangold, Aymeric Dieuleveut
Published: 2026-01-11
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.07021v1

We propose a novel analysis of the Decentralized Stochastic Gradient Descent (DSGD) algorithm with constant step size, interpreting the iterates of the algorithm as a Markov chain. We show that DSGD converges to a stationary distribution, with its bias, to first order, decomposable into two components: one due to decentralization (growing with the graph's spectral gap and clients' heterogeneity) and one due to stochasticity. Remarkably, the variance of local parameters is, at the first-order, inversely proportional to the number of clients, regardless of the network topology and even when clients' iterates are not averaged at the end. As a consequence of our analysis, we obtain non-asymptotic convergence bounds for clients' local iterates, confirming that DSGD has linear speed-up in the number of clients, and that the network topology only impacts higher-order terms.

---

### TurkBench: A Benchmark for Evaluating Turkish Large Language Models

Authors: Çağrı Toraman, Ahmet Kaan Sever, Ayse Aysu Cengiz, Elif Ecem Arslan, Görkem Sevinç, Mete Mert Birdal, Yusuf Faruk Güldemir, Ali Buğra Kanburoğlu, Sezen Felekoğlu, Osman Gürlek, Sarp Kantar, Birsen Şahin Kütük et al.
Published: 2026-01-11
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2601.07020v2

With the recent surge in the development of large language models, the need for comprehensive and language-specific evaluation benchmarks has become critical. While significant progress has been made in evaluating English-language models, benchmarks for other languages, particularly those with unique linguistic characteristics such as Turkish, remain less developed. Our study introduces TurkBench, a comprehensive benchmark designed to assess the capabilities of generative large language models in the Turkish language. TurkBench involves 8,151 data samples across 21 distinct subtasks. These are organized under six main categories of evaluation: Knowledge, Language Understanding, Reasoning, Content Moderation, Turkish Grammar and Vocabulary, and Instruction Following. The diverse range of tasks and the culturally relevant data would provide researchers and developers with a valuable tool for evaluating their models and identifying areas for improvement. We further publish our benchmark for online submissions at https://huggingface.co/turkbench

---

### Zer0n: An AI-Assisted Vulnerability Discovery and Blockchain-Backed Integrity Framework

Authors: Harshil Parmar, Pushti Vyas, Prayers Khristi, Priyank Panchal
Published: 2026-01-11
Categories: cs.CR, cs.AI, cs.SE
arXiv: https://arxiv.org/abs/2601.07019v1

As vulnerability research increasingly adopts generative AI, a critical reliance on opaque model outputs has emerged, creating a "trust gap" in security automation. We address this by introducing Zer0n, a framework that anchors the reasoning capabilities of Large Language Models (LLMs) to the immutable audit trails of blockchain technology. Specifically, we integrate Gemini 2.0 Pro for logic-based vulnerability detection with the Avalanche C-Chain for tamper-evident artifact logging. Unlike fully decentralized solutions that suffer from high latency, Zer0n employs a hybrid architecture: execution remains off-chain for performance, while integrity proofs are finalized on-chain. Our evaluation on a dataset of 500 endpoints reveals that this approach achieves 80% detection accuracy with only a marginal 22.9% overhead, effectively demonstrating that decentralized integrity can coexist with high-speed security workflows.

---

### Belief in False Information: A Human-Centered Security Risk in Sociotechnical Systems

Authors: Fabian Walke, Thaddäa Nürnberger
Published: 2026-01-11
Categories: cs.SI, cs.AI, cs.CR, cs.CY
arXiv: https://arxiv.org/abs/2601.07016v1

This paper provides a comprehensive literature review on the belief in false information, including misinformation, disinformation, and fake information. It addresses the increasing societal concern regarding false information, which is fueled by technological progress, especially advancements in artificial intelligence. This review systematically identifies and categorizes factors that influence the belief in false information. The review identifies 24 influence factors grouped into six main categories: demographic factors, personality traits, psychological factors, policy and values, media consumption, and preventive factors. Key findings highlight that lower education levels, high extraversion, low agreeableness, high neuroticism, and low cognitive reflection significantly increase belief in false information. The effectiveness of preventive strategies like labeling false information and promoting reflection about correctness is also discussed. This literature review conceptualizes belief in false information as a human-centered security risk in sociotechnical systems, as it can be exploited to manipulate decisions, undermine trust, and increase susceptibility to social engineering. It aims to inform preventive strategies that strengthen socio-technical security and societal resilience.

---

### Conditional Normalizing Flows for Forward and Backward Joint State and Parameter Estimation

Authors: Luke S. Lagunowich, Guoxiang Grayson Tong, Daniele E. Schiavazzi
Published: 2026-01-11
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2601.07013v2

Traditional filtering algorithms for state estimation -- such as classical Kalman filtering, unscented Kalman filtering, and particle filters -- show performance degradation when applied to nonlinear systems whose uncertainty follows arbitrary non-Gaussian, and potentially multi-modal distributions. This study reviews recent approaches to state estimation via nonlinear filtering based on conditional normalizing flows, where the conditional embedding is generated by standard MLP architectures, transformers or selective state-space models (like Mamba-SSM). In addition, we test the effectiveness of an optimal-transport-inspired kinetic loss term in mitigating overparameterization in flows consisting of a large collection of transformations. We investigate the performance of these approaches on applications relevant to autonomous driving and patient population dynamics, paying special attention to how they handle time inversion and chained predictions. Finally, we assess the performance of various conditioning strategies for an application to real-world COVID-19 joint SIR system forecasting and parameter estimation.

---

### Lexicalized Constituency Parsing for Middle Dutch: Low-resource Training and Cross-Domain Generalization

Authors: Yiming Liang, Fang Zhao
Published: 2026-01-11
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.07008v1

Recent years have seen growing interest in applying neural networks and contextualized word embeddings to the parsing of historical languages. However, most advances have focused on dependency parsing, while constituency parsing for low-resource historical languages like Middle Dutch has received little attention. In this paper, we adapt a transformer-based constituency parser to Middle Dutch, a highly heterogeneous and low-resource language, and investigate methods to improve both its in-domain and cross-domain performance. We show that joint training with higher-resource auxiliary languages increases F1 scores by up to 0.73, with the greatest gains achieved from languages that are geographically and temporally closer to Middle Dutch. We further evaluate strategies for leveraging newly annotated data from additional domains, finding that fine-tuning and data combination yield comparable improvements, and our neural parser consistently outperforms the currently used PCFG-based parser for Middle Dutch. We further explore feature-separation techniques for domain adaptation and demonstrate that a minimum threshold of approximately 200 examples per domain is needed to effectively enhance cross-domain performance.

---

### LLM Performance Predictors: Learning When to Escalate in Hybrid Human-AI Moderation Systems

Authors: Or Bachar, Or Levi, Sardhendu Mishra, Adi Levi, Manpreet Singh Minhas, Justin Miller, Omer Ben-Porat, Eilon Sheetrit, Jonathan Morra
Published: 2026-01-11
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.07006v1

As LLMs are increasingly integrated into human-in-the-loop content moderation systems, a central challenge is deciding when their outputs can be trusted versus when escalation for human review is preferable. We propose a novel framework for supervised LLM uncertainty quantification, learning a dedicated meta-model based on LLM Performance Predictors (LPPs) derived from LLM outputs: log-probabilities, entropy, and novel uncertainty attribution indicators. We demonstrate that our method enables cost-aware selective classification in real-world human-AI workflows: escalating high-risk cases while automating the rest. Experiments across state-of-the-art LLMs, including both off-the-shelf (Gemini, GPT) and open-source (Llama, Qwen), on multimodal and multilingual moderation tasks, show significant improvements over existing uncertainty estimators in accuracy-cost trade-offs. Beyond uncertainty estimation, the LPPs enhance explainability by providing new insights into failure conditions (e.g., ambiguous content vs. under-specified policy). This work establishes a principled framework for uncertainty-aware, scalable, and responsible human-AI moderation workflows.

---

### MicLog: Towards Accurate and Efficient LLM-based Log Parsing via Progressive Meta In-Context Learning

Authors: Jianbo Yu, Yixuan Li, Hai Xu, Kang Xu, Junjielong Xu, Zhijing Li, Pinjia He, Wanyuan Wang
Published: 2026-01-11
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2601.07005v1

Log parsing converts semi-structured logs into structured templates, forming a critical foundation for downstream analysis. Traditional syntax and semantic-based parsers often struggle with semantic variations in evolving logs and data scarcity stemming from their limited domain coverage. Recent large language model (LLM)-based parsers leverage in-context learning (ICL) to extract semantics from examples, demonstrating superior accuracy. However, LLM-based parsers face two main challenges: 1) underutilization of ICL capabilities, particularly in dynamic example selection and cross-domain generalization, leading to inconsistent performance; 2) time-consuming and costly LLM querying. To address these challenges, we present MicLog, the first progressive meta in-context learning (ProgMeta-ICL) log parsing framework that combines meta-learning with ICL on small open-source LLMs (i.e., Qwen-2.5-3B). Specifically, MicLog: i) enhances LLMs' ICL capability through a zero-shot to k-shot ProgMeta-ICL paradigm, employing weighted DBSCAN candidate sampling and enhanced BM25 demonstration selection; ii) accelerates parsing via a multi-level pre-query cache that dynamically matches and refines recently parsed templates. Evaluated on Loghub-2.0, MicLog achieves 10.3% higher parsing accuracy than the state-of-the-art parser while reducing parsing time by 42.4%.

---

### MemTrust: A Zero-Trust Architecture for Unified AI Memory System

Authors: Xing Zhou, Dmitrii Ustiugov, Haoxin Shang, Kisson Lin
Published: 2026-01-11
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2601.07004v1

AI memory systems are evolving toward unified context layers that enable efficient cross-agent collaboration and multi-tool workflows, facilitating better accumulation of personal data and learning of user preferences. However, centralization creates a trust crisis where users must entrust cloud providers with sensitive digital memory data. We identify a core tension between personalization demands and data sovereignty: centralized memory systems enable efficient cross-agent collaboration but expose users' sensitive data to cloud provider risks, while private deployments provide security but limit collaboration. To resolve this tension, we aim to achieve local-equivalent security while enabling superior maintenance efficiency and collaborative capabilities. We propose a five-layer architecture abstracting common functional components of AI memory systems: Storage, Extraction, Learning, Retrieval, and Governance. By applying TEE protection to each layer, we establish a trustworthy framework. Based on this, we design MemTrust, a hardware-backed zero-trust architecture that provides cryptographic guarantees across all layers. Our contributions include the five-layer abstraction, "Context from MemTrust" protocol for cross-application sharing, side-channel hardened retrieval with obfuscated access patterns, and comprehensive security analysis. The architecture enables third-party developers to port existing systems with acceptable development costs, achieving system-wide trustworthiness. We believe that AI memory plays a crucial role in enhancing the efficiency and collaboration of agents and AI tools. AI memory will become the foundational infrastructure for AI agents, and MemTrust serves as a universal trusted framework for AI memory systems, with the goal of becoming the infrastructure of memory infrastructure.

---

### Unity Forests: Improving Interaction Modelling and Interpretability in Random Forests

Authors: Roman Hornung, Alexander Hapfelmeier
Published: 2026-01-11
Categories: stat.ME, cs.LG, stat.CO
arXiv: https://arxiv.org/abs/2601.07003v1

Random forests (RFs) are widely used for prediction and variable importance analysis and are often believed to capture any types of interactions via recursive splitting. However, since the splits are chosen locally, interactions are only reliably captured when at least one involved covariate has a marginal effect. We introduce unity forests (UFOs), an RF variant designed to better exploit interactions involving covariates without marginal effects. In UFOs, the first few splits of each tree are optimized jointly across a random covariate subset to form a "tree root" capturing such interactions; the remainder is grown conventionally. We further propose the unity variable importance measure (VIM), which is based on out-of-bag split criterion values from the tree roots. Here, only a small fraction of tree root splits with the highest in-bag criterion values are considered per covariate, reflecting that covariates with purely interaction-based effects are discriminative only if a split in an interacting covariate occurred earlier in the tree. Finally, we introduce covariate-representative tree roots (CRTRs), which select representative tree roots per covariate and provide interpretable insight into the conditions - marginal or interactive - under which each covariate has its strongest effects. In a simulation study, the unity VIM reliably identified interacting covariates without marginal effects, unlike conventional RF-based VIMs. In a large-scale real-data comparison, UFOs achieved higher discrimination and predictive accuracy than standard RFs, with comparable calibration. The CRTRs reproduced the covariates' true effect types reliably in simulated data and provided interesting insights in a real data analysis.

---

### Spatial Multi-Task Learning for Breast Cancer Molecular Subtype Prediction from Single-Phase DCE-MRI

Authors: Sen Zeng, Hong Zhou, Zheng Zhu, Yang Liu
Published: 2026-01-11
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.07001v1

Accurate molecular subtype classification is essential for personalized breast cancer treatment, yet conventional immunohistochemical analysis relies on invasive biopsies and is prone to sampling bias. Although dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) enables non-invasive tumor characterization, clinical workflows typically acquire only single-phase post-contrast images to reduce scan time and contrast agent dose. In this study, we propose a spatial multi-task learning framework for breast cancer molecular subtype prediction from clinically practical single-phase DCE-MRI. The framework simultaneously predicts estrogen receptor (ER), progesterone receptor (PR), human epidermal growth factor receptor 2 (HER2) status, and the Ki-67 proliferation index -- biomarkers that collectively define molecular subtypes. The architecture integrates a deep feature extraction network with multi-scale spatial attention to capture intratumoral and peritumoral characteristics, together with a region-of-interest weighting module that emphasizes the tumor core, rim, and surrounding tissue. Multi-task learning exploits biological correlations among biomarkers through shared representations with task-specific prediction branches. Experiments on a dataset of 960 cases (886 internal cases split 7:1:2 for training/validation/testing, and 74 external cases evaluated via five-fold cross-validation) demonstrate that the proposed method achieves an AUC of 0.893, 0.824, and 0.857 for ER, PR, and HER2 classification, respectively, and a mean absolute error of 8.2\% for Ki-67 regression, significantly outperforming radiomics and single-task deep learning baselines. These results indicate the feasibility of accurate, non-invasive molecular subtype prediction using standard imaging protocols.

---

### ObjSplat: Geometry-Aware Gaussian Surfels for Active Object Reconstruction

Authors: Yuetao Li, Zhizhou Jia, Yu Zhang, Qun Hao, Shaohui Zhang
Published: 2026-01-11
Categories: cs.RO, cs.CV
arXiv: https://arxiv.org/abs/2601.06997v2

Autonomous high-fidelity object reconstruction is fundamental for creating digital assets and bridging the simulation-to-reality gap in robotics. We present ObjSplat, an active reconstruction framework that leverages Gaussian surfels as a unified representation to progressively reconstruct unknown objects with both photorealistic appearance and accurate geometry. Addressing the limitations of conventional opacity or depth-based cues, we introduce a geometry-aware viewpoint evaluation pipeline that explicitly models back-face visibility and occlusion-aware multi-view covisibility, reliably identifying under-reconstructed regions even on geometrically complex objects. Furthermore, to overcome the limitations of greedy planning strategies, ObjSplat employs a next-best-path (NBP) planner that performs multi-step lookahead on a dynamically constructed spatial graph. By jointly optimizing information gain and movement cost, this planner generates globally efficient trajectories. Extensive experiments in simulation and on real-world cultural artifacts demonstrate that ObjSplat produces physically consistent models within minutes, achieving superior reconstruction fidelity and surface completeness while significantly reducing scan time and path length compared to state-of-the-art approaches. Project page: https://li-yuetao.github.io/ObjSplat-page/ .

---

### Can Textual Reasoning Improve the Performance of MLLMs on Fine-grained Visual Classification?

Authors: Jie Zhu, Yiyang Su, Xiaoming Liu
Published: 2026-01-11
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.06993v2

Multi-modal large language models (MLLMs) exhibit strong general-purpose capabilities, yet still struggle on Fine-Grained Visual Classification (FGVC), a core perception task that requires subtle visual discrimination and is crucial for many real-world applications. A widely adopted strategy for boosting performance on challenging tasks such as math and coding is Chain-of-Thought (CoT) reasoning. However, several prior works have reported that CoT can actually harm performance on visual perception tasks. These studies, though, examine the issue from relatively narrow angles and leave open why CoT degrades perception-heavy performance. We systematically re-examine the role of CoT in FGVC through the lenses of zero-shot evaluation and multiple training paradigms. Across these settings, we uncover a central paradox: the degradation induced by CoT is largely driven by the reasoning length, in which longer textual reasoning consistently lowers classification accuracy. We term this phenomenon the ``Cost of Thinking''. Building on this finding, we make two key contributions: (1) MRN, a simple and general plug-and-play normalization method for multi-reward optimization that balances heterogeneous reward signals, and (2) ReFine-RFT, a framework that combines ensemble rewards with MRN to constrain reasoning length while providing dense accuracy-oriented feedback. Extensive experiments demonstrate the effectiveness of our findings and the proposed ReFine-RFT, achieving state-of-the-art performance across FGVC benchmarks. Project page: \href{https://refine-rft.github.io/}{ReFine-RFT}.

---

### FinCARDS: Card-Based Analyst Reranking for Financial Document Question Answering

Authors: Yixi Zhou, Fan Zhang, Yu Chen, Haipeng Zhang, Preslav Nakov, Zhuohan Xie
Published: 2026-01-11
Categories: cs.IR, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2601.06992v2

Financial question answering (QA) over long corporate filings requires evidence to satisfy strict constraints on entities, financial metrics, fiscal periods, and numeric values. However, existing LLM-based rerankers primarily optimize semantic relevance, leading to unstable rankings and opaque decisions on long documents. We propose FinCards, a structured reranking framework that reframes financial evidence selection as constraint satisfaction under a finance-aware schema. FinCards represents filing chunks and questions using aligned schema fields (entities, metrics, periods, and numeric spans), enabling deterministic field-level matching. Evidence is selected via a multi-stage tournament reranking with stability-aware aggregation, producing auditable decision traces. Across two corporate filing QA benchmarks, FinCards substantially improves early-rank retrieval over both lexical and LLM-based reranking baselines, while reducing ranking variance, without requiring model fine-tuning or unpredictable inference budgets. Our code is available at https://github.com/XanderZhou2022/FINCARDS.

---

### Match Made with Matrix Completion: Efficient Learning under Matching Interference

Authors: Zhiyuan Tang, Wanning Chen, Kan Xu
Published: 2026-01-11
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2601.06982v1

Matching markets face increasing needs to learn the matching qualities between demand and supply for effective design of matching policies. In practice, the matching rewards are high-dimensional due to the growing diversity of participants. We leverage a natural low-rank matrix structure of the matching rewards in these two-sided markets, and propose to utilize matrix completion to accelerate reward learning with limited offline data. A unique property for matrix completion in this setting is that the entries of the reward matrix are observed with matching interference -- i.e., the entries are not observed independently but dependently due to matching or budget constraints. Such matching dependence renders unique technical challenges, such as sub-optimality or inapplicability of the existing analytical tools in the matrix completion literature, since they typically rely on sample independence. In this paper, we first show that standard nuclear norm regularization remains theoretically effective under matching interference. We provide a near-optimal Frobenius norm guarantee in this setting, coupled with a new analytical technique. Next, to guide certain matching decisions, we develop a novel ``double-enhanced'' estimator, based off the nuclear norm estimator, with a near-optimal entry-wise guarantee. Our double-enhancement procedure can apply to broader sampling schemes even with dependence, which may be of independent interest. Additionally, we extend our approach to online learning settings with matching constraints such as optimal matching and stable matching, and present improved regret bounds in matrix dimensions. Finally, we demonstrate the practical value of our methods using both synthetic data and real data of labor markets.

---

### MedTutor: A Retrieval-Augmented LLM System for Case-Based Medical Education

Authors: Dongsuk Jang, Ziyao Shangguan, Kyle Tegtmeyer, Anurag Gupta, Jan Czerminski, Sophie Chheang, Arman Cohan
Published: 2026-01-11
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.06979v2

The learning process for medical residents presents significant challenges, demanding both the ability to interpret complex case reports and the rapid acquisition of accurate medical knowledge from reliable sources. Residents typically study case reports and engage in discussions with peers and mentors, but finding relevant educational materials and evidence to support their learning from these cases is often time-consuming and challenging. To address this, we introduce MedTutor, a novel system designed to augment resident training by automatically generating evidence-based educational content and multiple-choice questions from clinical case reports. MedTutor leverages a Retrieval-Augmented Generation (RAG) pipeline that takes clinical case reports as input and produces targeted educational materials. The system's architecture features a hybrid retrieval mechanism that synergistically queries a local knowledge base of medical textbooks and academic literature (using PubMed, Semantic Scholar APIs) for the latest related research, ensuring the generated content is both foundationally sound and current. The retrieved evidence is filtered and ordered using a state-of-the-art reranking model and then an LLM generates the final long-form output describing the main educational content regarding the case-report. We conduct a rigorous evaluation of the system. First, three radiologists assessed the quality of outputs, finding them to be of high clinical and educational value. Second, we perform a large scale evaluation using an LLM-as-a Judge to understand if LLMs can be used to evaluate the output of the system. Our analysis using correlation between LLMs outputs and human expert judgments reveals a moderate alignment and highlights the continued necessity of expert oversight.

---

### Benchmarking Autonomy in Scientific Experiments: A Hierarchical Taxonomy for Autonomous Large-Scale Facilities

Authors: James Le Houx
Published: 2026-01-11
Categories: physics.ins-det, cond-mat.mtrl-sci, cs.AI, cs.RO
arXiv: https://arxiv.org/abs/2601.06978v1

The transition from automated data collection to fully autonomous discovery requires a shared vocabulary to benchmark progress. While the automotive industry relies on the SAE J3016 standard, current taxonomies for autonomous science presuppose an owner-operator model that is incompatible with the operational rigidities of Large-Scale User Facilities. Here, we propose the Benchmarking Autonomy in Scientific Experiments (BASE) Scale, a 6-level taxonomy (Levels 0-5) specifically adapted for these unique constraints. Unlike owner-operator models, User Facilities require zero-shot deployment where agents must operate immediately without extensive training periods. We define the specific technical requirements for each tier, identifying the Inference Barrier (Level 3) as the critical latency threshold where decisions shift from scalar feedback to semantic digital twins. Fundamentally, this level extends the decision manifold from spatial exploration to temporal gating, enabling the agent to synchronise acquisition with the onset of transient physical events. By establishing these operational definitions, the BASE Scale provides facility directors, funding bodies, and beamline scientists with a standardised metric to assess risk, define liability, and quantify the intelligence of experimental workflows.

---

### UETQuintet at BioCreative IX -- MedHopQA: Enhancing Biomedical QA with Selective Multi-hop Reasoning and Contextual Retrieval

Authors: Quoc-An Nguyen, Thi-Minh-Thu Vu, Bich-Dat Nguyen, Dinh-Quang-Minh Tran, Hoang-Quynh Le
Published: 2026-01-11
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.06974v1

Biomedical Question Answering systems play a critical role in processing complex medical queries, yet they often struggle with the intricate nature of medical data and the demand for multi-hop reasoning. In this paper, we propose a model designed to effectively address both direct and sequential questions. While sequential questions are decomposed into a chain of sub-questions to perform reasoning across a chain of steps, direct questions are processed directly to ensure efficiency and minimise processing overhead. Additionally, we leverage multi-source information retrieval and in-context learning to provide rich, relevant context for generating answers. We evaluated our model on the BioCreative IX - MedHopQA Shared Task datasets. Our approach achieves an Exact Match score of 0.84, ranking second on the current leaderboard. These results highlight the model's capability to meet the challenges of Biomedical Question Answering, offering a versatile solution for advancing medical research and practice.

---

### LLMs Can't Play Hangman: On the Necessity of a Private Working Memory for Language Agents

Authors: Davide Baldelli, Ali Parviz, Amal Zouaq, Sarath Chandar
Published: 2026-01-11
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.06973v3

As LLMs move from text completion toward autonomous agents, they remain constrained by the standard chat interface, which lacks private working memory. This raises a fundamental question: can agents reliably perform interactive tasks that depend on hidden state? We define Private State Interactive Tasks (PSITs), which require agents to generate and maintain hidden information while producing public responses consistent with a fixed hidden state. We show theoretically that any agent restricted to the public conversation history cannot both keep the secret unresolved in the transcript and respond consistently with a fixed hidden state in PSITs, yielding an architectural impossibility theorem. To empirically validate this limitation, we introduce a self-consistency testing protocol that evaluates whether agents can maintain a hidden secret across forked dialogue branches. Standard chat-based LLMs and retrieval-based memory baselines fail this test regardless of scale, demonstrating that semantic retrieval does not enable true state maintenance. To address this, we propose a novel architecture incorporating an explicit private working memory; we demonstrate that this mechanism restores consistency with a fixed hidden state, establishing private state as a necessary component for PSIT-capable language agents. Our code is available at https://github.com/chandar-lab/Hangman

---

### Categorize Early, Integrate Late: Divergent Processing Strategies in Automatic Speech Recognition

Authors: Nathan Roll, Pranav Bhalerao, Martijn Bartelds, Arjun Pawar, Yuka Tatsumi, Tolulope Ogunremi, Chen Shani, Calbert Graham, Meghan Sumner, Dan Jurafsky
Published: 2026-01-11
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.06972v2

In speech language modeling, two architectures dominate the frontier: the Transformer and the Conformer. However, it remains unknown whether their comparable performance stems from convergent processing strategies or distinct architectural inductive biases. We introduce Architectural Fingerprinting, a probing framework that isolates the effect of architecture on representation, and apply it to a controlled suite of 24 pre-trained encoders (39M-3.3B parameters). Our analysis reveals divergent hierarchies: Conformers implement a "Categorize Early" strategy, resolving phoneme categories 29% earlier in depth and speaker gender by 16% depth. In contrast, Transformers "Integrate Late," deferring phoneme, accent, and duration encoding to deep layers (49-57%). These fingerprints suggest design heuristics: Conformers' front-loaded categorization may benefit low-latency streaming, while Transformers' deep integration may favor tasks requiring rich context and cross-utterance normalization.

---

### Generalization Bounds for Transformer Channel Decoders

Authors: Qinshan Zhang, Bin Chen, Yong Jiang, Shu-Tao Xia
Published: 2026-01-11
Categories: cs.IT, cs.LG
arXiv: https://arxiv.org/abs/2601.06969v1

Transformer channel decoders, such as the Error Correction Code Transformer (ECCT), have shown strong empirical performance in channel decoding, yet their generalization behavior remains theoretically unclear. This paper studies the generalization performance of ECCT from a learning-theoretic perspective. By establishing a connection between multiplicative noise estimation errors and bit-error-rate (BER), we derive an upper bound on the generalization gap via bit-wise Rademacher complexity. The resulting bound characterizes the dependence on code length, model parameters, and training set size, and applies to both single-layer and multi-layer ECCTs. We further show that parity-check-based masked attention induces sparsity that reduces the covering number, leading to a tighter generalization bound. To the best of our knowledge, this work provides the first theoretical generalization guarantees for this class of decoders.

---

### A Robust Certified Machine Unlearning Method Under Distribution Shift

Authors: Jinduo Guo, Yinzhi Cao
Published: 2026-01-11
Categories: cs.LG, cs.CR
arXiv: https://arxiv.org/abs/2601.06967v1

The Newton method has been widely adopted to achieve certified unlearning. A critical assumption in existing approaches is that the data requested for unlearning are selected i.i.d.(independent and identically distributed). However,the problem of certified unlearning under non-i.i.d. deletions remains largely unexplored. In practice, unlearning requests are inherently biased, leading to non-i.i.d. deletions and causing distribution shifts between the original and retained datasets. In this paper, we show that certified unlearning with the Newton method becomes inefficient and ineffective under non-i.i.d. unlearning sets. We then propose a better certified unlearning approach by performing a distribution-aware certified unlearning framework based on iterative Newton updates constrained by a trust region. Our method provides a closer approximation to the retrained model and yields a tighter pre-run bound on the gradient residual, thereby ensuring efficient (epsilon, delta)-certified unlearning. To demonstrate its practical effectiveness under distribution shift, we also conduct extensive experiments across multiple evaluation metrics, providing a comprehensive assessment of our approach.

---

### RealMem: Benchmarking LLMs in Real-World Memory-Driven Interaction

Authors: Haonan Bian, Zhiyuan Yao, Sen Hu, Zishan Xu, Shaolei Zhang, Yifu Guo, Ziliang Yang, Xueran Han, Huacan Wang, Ronghao Chen
Published: 2026-01-11
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2601.06966v1

As Large Language Models (LLMs) evolve from static dialogue interfaces to autonomous general agents, effective memory is paramount to ensuring long-term consistency. However, existing benchmarks primarily focus on casual conversation or task-oriented dialogue, failing to capture **"long-term project-oriented"** interactions where agents must track evolving goals. To bridge this gap, we introduce **RealMem**, the first benchmark grounded in realistic project scenarios. RealMem comprises over 2,000 cross-session dialogues across eleven scenarios, utilizing natural user queries for evaluation. We propose a synthesis pipeline that integrates Project Foundation Construction, Multi-Agent Dialogue Generation, and Memory and Schedule Management to simulate the dynamic evolution of memory. Experiments reveal that current memory systems face significant challenges in managing the long-term project states and dynamic context dependencies inherent in real-world projects. Our code and datasets are available at (https://github.com/AvatarMemory/RealMemBench)(https://github.com/AvatarMemory/RealMemBench).

---