# Research Papers — 2026-01 · bundle page 178 of 189

> Full-text markdown of papers #8851–8900 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/178
[← Previous bundle](https://aipod.dev/papers/archive/2026-01/page/177.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-01/page/179.md)

### Sim2Real SAR Image Restoration: Metadata-Driven Models for Joint Despeckling and Sidelobes Reduction

Authors: Antoine De Paepe, Pascal Nguyen, Michael Mabelle, Cédric Saleun, Antoine Jouadé, Jean-Christophe Louvigne
Published: 2026-01-04
Categories: eess.IV, cs.CV, eess.SP
arXiv: https://arxiv.org/abs/2601.01541v1

Synthetic aperture radar (SAR) provides valuable information about the Earth's surface under all weather and illumination conditions. However, the inherent phenomenon of speckle and the presence of sidelobes around bright targets pose challenges for accurate interpretation of SAR imagery. Most existing SAR image restoration methods address despeckling and sidelobes reduction as separate tasks. In this paper, we propose a unified framework that jointly performs both tasks using neural networks (NNs) trained on a realistic SAR simulated dataset generated with MOCEM. Inference can then be performed on real SAR images, demonstrating effective simulation to real (Sim2Real) transferability. Additionally, we incorporate acquisition metadata as auxiliary input to the NNs, demonstrating improved restoration performance.

---

### FAR-AMTN: Attention Multi-Task Network for Face Attribute Recognition

Authors: Gong Gao, Zekai Wang, Xianhui Liu, Weidong Zhao
Published: 2026-01-04
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.01537v1

To enhance the generalization performance of Multi-Task Networks (MTN) in Face Attribute Recognition (FAR), it is crucial to share relevant information across multiple related prediction tasks effectively. Traditional MTN methods create shared low-level modules and distinct high-level modules, causing an exponential increase in model parameters with the addition of tasks. This approach also limits feature interaction at the high level, hindering the exploration of semantic relations among attributes, thereby affecting generalization negatively. In response, this study introduces FAR-AMTN, a novel Attention Multi-Task Network for FAR. It incorporates a Weight-Shared Group-Specific Attention (WSGSA) module with shared parameters to minimize complexity while improving group feature representation. Furthermore, a Cross-Group Feature Fusion (CGFF) module is utilized to foster interactions between attribute groups, enhancing feature learning. A Dynamic Weighting Strategy (DWS) is also introduced for synchronized task convergence. Experiments on the CelebA and LFWA datasets demonstrate that the proposed FAR-AMTN demonstrates superior accuracy with significantly fewer parameters compared to existing models.

---

### Improving Flexible Image Tokenizers for Autoregressive Image Generation

Authors: Zixuan Fu, Lanqing Guo, Chong Wang, Binbin Song, Ding Liu, Bihan Wen
Published: 2026-01-04
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.01535v1

Flexible image tokenizers aim to represent an image using an ordered 1D variable-length token sequence. This flexible tokenization is typically achieved through nested dropout, where a portion of trailing tokens is randomly truncated during training, and the image is reconstructed using the remaining preceding sequence. However, this tail-truncation strategy inherently concentrates the image information in the early tokens, limiting the effectiveness of downstream AutoRegressive (AR) image generation as the token length increases. To overcome these limitations, we propose \textbf{ReToK}, a flexible tokenizer with \underline{Re}dundant \underline{Tok}en Padding and Hierarchical Semantic Regularization, designed to fully exploit all tokens for enhanced latent modeling. Specifically, we introduce \textbf{Redundant Token Padding} to activate tail tokens more frequently, thereby alleviating information over-concentration in the early tokens. In addition, we apply \textbf{Hierarchical Semantic Regularization} to align the decoding features of earlier tokens with those from a pre-trained vision foundation model, while progressively reducing the regularization strength toward the tail to allow finer low-level detail reconstruction. Extensive experiments demonstrate the effectiveness of ReTok: on ImageNet 256$\times$256, our method achieves superior generation performance compared with both flexible and fixed-length tokenizers. Code will be available at: \href{https://github.com/zfu006/ReTok}{https://github.com/zfu006/ReTok}

---

### Aletheia: Quantifying Cognitive Conviction in Reasoning Models via Regularized Inverse Confusion Matrix

Authors: Fanzhe Fu
Published: 2026-01-04
Categories: cs.AI, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2601.01532v1

In the progressive journey toward Artificial General Intelligence (AGI), current evaluation paradigms face an epistemological crisis. Static benchmarks measure knowledge breadth but fail to quantify the depth of belief. While Simhi et al. (2025) defined the CHOKE phenomenon in standard QA, we extend this framework to quantify "Cognitive Conviction" in System 2 reasoning models. We propose Project Aletheia, a cognitive physics framework that employs Tikhonov Regularization to invert the judge's confusion matrix. To validate this methodology without relying on opaque private data, we implement a Synthetic Proxy Protocol. Our preliminary pilot study on 2025 baselines (e.g., DeepSeek-R1, OpenAI o1) suggests that while reasoning models act as a "cognitive buffer," they may exhibit "Defensive OverThinking" under adversarial pressure. Furthermore, we introduce the Aligned Conviction Score (S_aligned) to verify that conviction does not compromise safety. This work serves as a blueprint for measuring AI scientific integrity.

---

### EmoHarbor: Evaluating Personalized Emotional Support by Simulating the User's Internal World

Authors: Jing Ye, Lu Xiang, Yaping Zhang, Chengqing Zong
Published: 2026-01-04
Categories: cs.CL, cs.HC
arXiv: https://arxiv.org/abs/2601.01530v1

Current evaluation paradigms for emotional support conversations tend to reward generic empathetic responses, yet they fail to assess whether the support is genuinely personalized to users' unique psychological profiles and contextual needs. We introduce EmoHarbor, an automated evaluation framework that adopts a User-as-a-Judge paradigm by simulating the user's inner world. EmoHarbor employs a Chain-of-Agent architecture that decomposes users' internal processes into three specialized roles, enabling agents to interact with supporters and complete assessments in a manner similar to human users. We instantiate this benchmark using 100 real-world user profiles that cover a diverse range of personality traits and situations, and define 10 evaluation dimensions of personalized support quality. Comprehensive evaluation of 20 advanced LLMs on EmoHarbor reveals a critical insight: while these models excel at generating empathetic responses, they consistently fail to tailor support to individual user contexts. This finding reframes the central challenge, shifting research focus from merely enhancing generic empathy to developing truly user-aware emotional support. EmoHarbor provides a reproducible and scalable framework to guide the development and evaluation of more nuanced and user-aware emotional support systems.

---

### DrivingGen: A Comprehensive Benchmark for Generative Video World Models in Autonomous Driving

Authors: Yang Zhou, Hao Shao, Letian Wang, Zhuofan Zong, Hongsheng Li, Steven L. Waslander
Published: 2026-01-04
Categories: cs.CV, cs.AI, cs.RO
arXiv: https://arxiv.org/abs/2601.01528v2

Video generation models, as one form of world models, have emerged as one of the most exciting frontiers in AI, promising agents the ability to imagine the future by modeling the temporal evolution of complex scenes. In autonomous driving, this vision gives rise to driving world models: generative simulators that imagine ego and agent futures, enabling scalable simulation, safe testing of corner cases, and rich synthetic data generation. Yet, despite fast-growing research activity, the field lacks a rigorous benchmark to measure progress and guide priorities. Existing evaluations remain limited: generic video metrics overlook safety-critical imaging factors; trajectory plausibility is rarely quantified; temporal and agent-level consistency is neglected; and controllability with respect to ego conditioning is ignored. Moreover, current datasets fail to cover the diversity of conditions required for real-world deployment. To address these gaps, we present DrivingGen, the first comprehensive benchmark for generative driving world models. DrivingGen combines a diverse evaluation dataset curated from both driving datasets and internet-scale video sources, spanning varied weather, time of day, geographic regions, and complex maneuvers, with a suite of new metrics that jointly assess visual realism, trajectory plausibility, temporal coherence, and controllability. Benchmarking 14 state-of-the-art models reveals clear trade-offs: general models look better but break physics, while driving-specific ones capture motion realistically but lag in visual quality. DrivingGen offers a unified evaluation framework to foster reliable, controllable, and deployable driving world models, enabling scalable simulation, planning, and data-driven decision-making.

---

### BARE: Towards Bias-Aware and Reasoning-Enhanced One-Tower Visual Grounding

Authors: Hongbing Li, Linhui Xiao, Zihan Zhao, Qi Shen, Yixiang Huang, Bo Xiao, Zhanyu Ma
Published: 2026-01-04
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.01526v1

Visual Grounding (VG), which aims to locate a specific region referred to by expressions, is a fundamental yet challenging task in the multimodal understanding fields. While recent grounding transfer works have advanced the field through one-tower architectures, they still suffer from two primary limitations: (1) over-entangled multimodal representations that exacerbate deceptive modality biases, and (2) insufficient semantic reasoning that hinders the comprehension of referential cues. In this paper, we propose BARE, a bias-aware and reasoning-enhanced framework for one-tower visual grounding. BARE introduces a mechanism that preserves modality-specific features and constructs referential semantics through three novel modules: (i) language salience modulator, (ii) visual bias correction and (iii) referential relationship enhancement, which jointly mitigate multimodal distractions and enhance referential comprehension. Extensive experimental results on five benchmarks demonstrate that BARE not only achieves state-of-the-art performance but also delivers superior computational efficiency compared to existing approaches. The code is publicly accessible at https://github.com/Marloweeee/BARE.

---

### Bayesian Orchestration of Multi-LLM Agents for Cost-Aware Sequential Decision-Making

Authors: Danial Amin
Published: 2026-01-04
Categories: cs.AI, cs.CL, cs.ET
arXiv: https://arxiv.org/abs/2601.01522v1

Large language models (LLMs) are increasingly deployed as autonomous decision agents in settings with asymmetric error costs: hiring (missed talent vs wasted interviews), medical triage (missed emergencies vs unnecessary escalation), and fraud detection (approved fraud vs declined legitimate payments). The dominant design queries a single LLM for a posterior over states, thresholds "confidence," and acts; we prove this is inadequate for sequential decisions with costs. We propose a Bayesian, cost-aware multi-LLM orchestration framework that treats LLMs as approximate likelihood models rather than classifiers. For each candidate state, we elicit likelihoods via contrastive prompting, aggregate across diverse models with robust statistics, and update beliefs with Bayes rule under explicit priors as new evidence arrives. This enables coherent belief updating, expected-cost action selection, principled information gathering via value of information, and fairness gains via ensemble bias mitigation. In resume screening with costs of 40000 USD per missed hire, 2500 USD per interview, and 150 USD per phone screen, experiments on 1000 resumes using five LLMs (GPT-4o, Claude 4.5 Sonnet, Gemini Pro, Grok, DeepSeek) reduce total cost by 294000 USD (34 percent) versus the best single-LLM baseline and improve demographic parity by 45 percent (max group gap 22 to 5 percentage points). Ablations attribute 51 percent of savings to multi-LLM aggregation, 43 percent to sequential updating, and 20 percent to disagreement-triggered information gathering, consistent with the theoretical benefits of correct probabilistic foundations.

---

### FastV-RAG: Towards Fast and Fine-Grained Video QA with Retrieval-Augmented Generation

Authors: Gen Li, Peiyu Liu
Published: 2026-01-04
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2601.01513v2

Vision-Language Models (VLMs) excel at visual reasoning but still struggle with integrating external knowledge. Retrieval-Augmented Generation (RAG) is a promising solution, but current methods remain inefficient and often fail to maintain high answer quality. To address these challenges, we propose VideoSpeculateRAG, an efficient VLM-based RAG framework built on two key ideas. First, we introduce a speculative decoding pipeline: a lightweight draft model quickly generates multiple answer candidates, which are then verified and refined by a more accurate heavyweight model, substantially reducing inference latency without sacrificing correctness. Second, we identify a major source of error - incorrect entity recognition in retrieved knowledge - and mitigate it with a simple yet effective similarity-based filtering strategy that improves entity alignment and boosts overall answer accuracy. Experiments demonstrate that VideoSpeculateRAG achieves comparable or higher accuracy than standard RAG approaches while accelerating inference by approximately 2x. Our framework highlights the potential of combining speculative decoding with retrieval-augmented reasoning to enhance efficiency and reliability in complex, knowledge-intensive multimodal tasks.

---

### A Novel Deep Learning Method for Segmenting the Left Ventricle in Cardiac Cine MRI

Authors: Wenhui Chu, Aobo Jin, Hardik A. Gohel
Published: 2026-01-04
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2601.01512v1

This research aims to develop a novel deep learning network, GBU-Net, utilizing a group-batch-normalized U-Net framework, specifically designed for the precise semantic segmentation of the left ventricle in short-axis cine MRI scans. The methodology includes a down-sampling pathway for feature extraction and an up-sampling pathway for detail restoration, enhanced for medical imaging. Key modifications include techniques for better contextual understanding crucial in cardiac MRI segmentation. The dataset consists of 805 left ventricular MRI scans from 45 patients, with comparative analysis using established metrics such as the dice coefficient and mean perpendicular distance. GBU-Net significantly improves the accuracy of left ventricle segmentation in cine MRI scans. Its innovative design outperforms existing methods in tests, surpassing standard metrics like the dice coefficient and mean perpendicular distance. The approach is unique in its ability to capture contextual information, often missed in traditional CNN-based segmentation. An ensemble of the GBU-Net attains a 97% dice score on the SunnyBrook testing dataset. GBU-Net offers enhanced precision and contextual understanding in left ventricle segmentation for surgical robotics and medical analysis.

---

### Reading Between the Lines: Deconfounding Causal Estimates using Text Embeddings and Deep Learning

Authors: Ahmed Dawoud, Osama El-Shamy
Published: 2026-01-04
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.01511v1

Estimating causal treatment effects in observational settings is frequently compromised by selection bias arising from unobserved confounders. While traditional econometric methods struggle when these confounders are orthogonal to structured covariates, high-dimensional unstructured text often contains rich proxies for these latent variables. This study proposes a Neural Network-Enhanced Double Machine Learning (DML) framework designed to leverage text embeddings for causal identification. Using a rigorous synthetic benchmark, we demonstrate that unstructured text embeddings capture critical confounding information that is absent from structured tabular data. However, we show that standard tree-based DML estimators retain substantial bias (+24%) due to their inability to model the continuous topology of embedding manifolds. In contrast, our deep learning approach reduces bias to -0.86% with optimized architectures, effectively recovering the ground-truth causal parameter. These findings suggest that deep learning architectures are essential for satisfying the unconfoundedness assumption when conditioning on high-dimensional natural language data

---

### DiffKD-DCIS: Predicting Upgrade of Ductal Carcinoma In Situ with Diffusion Augmentation and Knowledge Distillation

Authors: Tao Li, Qing Li, Na Li, Hui Xie
Published: 2026-01-04
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.01507v1

Accurately predicting the upgrade of ductal carcinoma in situ (DCIS) to invasive ductal carcinoma (IDC) is crucial for surgical planning. However, traditional deep learning methods face challenges due to limited ultrasound data and poor generalization ability. This study proposes the DiffKD-DCIS framework, integrating conditional diffusion modeling with teacher-student knowledge distillation. The framework operates in three stages: First, a conditional diffusion model generates high-fidelity ultrasound images using multimodal conditions for data augmentation. Then, a deep teacher network extracts robust features from both original and synthetic data. Finally, a compact student network learns from the teacher via knowledge distillation, balancing generalization and computational efficiency. Evaluated on a multi-center dataset of 1,435 cases, the synthetic images were of good quality. The student network had fewer parameters and faster inference. On external test sets, it outperformed partial combinations, and its accuracy was comparable to senior radiologists and superior to junior ones, showing significant clinical potential.

---

### Multiscale replay: A robust algorithm for stochastic variational inequalities with a Markovian buffer

Authors: Milind Nakul, Tianjiao Li, Ashwin Pananjady
Published: 2026-01-04
Categories: math.OC, stat.ML
arXiv: https://arxiv.org/abs/2601.01502v1

We introduce the Multiscale Experience Replay (MER) algorithm for solving a class of stochastic variational inequalities (VIs) in settings where samples are generated from a Markov chain and we have access to a memory buffer to store them. Rather than uniformly sampling from the buffer, MER utilizes a multi-scale sampling scheme to emulate the behavior of VI algorithms designed for independent and identically distributed samples, overcoming bias in the de facto serial scheme and thereby accelerating convergence. Notably, unlike standard sample-skipping variants of serial algorithms, MER is robust in that it achieves this acceleration in iteration complexity whenever possible, and without requiring knowledge of the mixing time of the Markov chain. We also discuss applications of MER, particularly in policy evaluation with temporal difference learning and in training generalized linear models with dependent data.

---

### Advanced Global Wildfire Activity Modeling with Hierarchical Graph ODE

Authors: Fan Xu, Wei Gong, Hao Wu, Lilan Peng, Nan Wang, Qingsong Wen, Xian Wu, Kun Wang, Xibin Zhao
Published: 2026-01-04
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.01501v1

Wildfires, as an integral component of the Earth system, are governed by a complex interplay of atmospheric, oceanic, and terrestrial processes spanning a vast range of spatiotemporal scales. Modeling their global activity on large timescales is therefore a critical yet challenging task. While deep learning has recently achieved significant breakthroughs in global weather forecasting, its potential for global wildfire behavior prediction remains underexplored. In this work, we reframe this problem and introduce the Hierarchical Graph ODE (HiGO), a novel framework designed to learn the multi-scale, continuous-time dynamics of wildfires. Specifically, we represent the Earth system as a multi-level graph hierarchy and propose an adaptive filtering message passing mechanism for both intra- and inter-level information flow, enabling more effective feature extraction and fusion. Furthermore, we incorporate GNN-parameterized Neural ODE modules at multiple levels to explicitly learn the continuous dynamics inherent to each scale. Through extensive experiments on the SeasFire Cube dataset, we demonstrate that HiGO significantly outperforms state-of-the-art baselines on long-range wildfire forecasting. Moreover, its continuous-time predictions exhibit strong observational consistency, highlighting its potential for real-world applications.

---

### From Failure to Mastery: Generating Hard Samples for Tool-use Agents

Authors: Bingguang Hao, Zengzhuang Xu, Yuntao Wen, Xinyi Xu, Yang Liu, Tong Zhao, Maolin Wang, Long Chen, Dong Wang, Yicheng Chen, Cunyin Peng, Xiangyu Zhao et al.
Published: 2026-01-04
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.01498v1

The advancement of LLM agents with tool-use capabilities requires diverse and complex training corpora. Existing data generation methods, which predominantly follow a paradigm of random sampling and shallow generation, often yield simple and homogeneous trajectories that fail to capture complex, implicit logical dependencies. To bridge this gap, we introduce HardGen, an automatic agentic pipeline designed to generate hard tool-use training samples with verifiable reasoning. Firstly, HardGen establishes a dynamic API Graph built upon agent failure cases, from which it samples to synthesize hard traces. Secondly, these traces serve as conditional priors to guide the instantiation of modular, abstract advanced tools, which are subsequently leveraged to formulate hard queries. Finally, the advanced tools and hard queries enable the generation of verifiable complex Chain-of-Thought (CoT), with a closed-loop evaluation feedback steering the continuous refinement of the process. Extensive evaluations demonstrate that a 4B parameter model trained with our curated dataset achieves superior performance compared to several leading open-source and closed-source competitors (e.g., GPT-5.2, Gemini-3-Pro and Claude-Opus-4.5). Our code, models, and dataset will be open-sourced to facilitate future research.

---

### On the Practical Estimation and Interpretation of Rényi Transfer Entropy

Authors: Zlata Tabachová, Petr Jizba, Hynek Lavička, Milan Paluš
Published: 2026-01-04
Categories: nlin.PS, stat.ML
arXiv: https://arxiv.org/abs/2601.01497v1

Rényi transfer entropy (RTE) is a generalization of classical transfer entropy that replaces Shannon's entropy with Rényi's information measure. This, in turn, introduces a new tunable parameter $α$, which accounts for sensitivity to low- or high-probability events. Although RTE shows strong potential for analyzing causal relations in complex, non-Gaussian systems, its practical use is limited, primarily due to challenges related to its accurate estimation and interpretation. These difficulties are especially pronounced when working with finite, high-dimensional, or heterogeneous datasets. In this paper, we systematically study the performance of a k-nearest neighbor estimator for both Rényi entropy (RE) and RTE using various synthetic data sets with clear cause-and-effect relationships inherent to their construction. We test the estimator across a broad range of parameters, including sample size, dimensionality, memory length, and Rényi order $α$. In particular, we apply the estimator to a set of simulated processes with increasing structural complexity, ranging from linear dynamics to nonlinear systems with multi-source couplings. To address interpretational challenges arising from potentially negative RE and RTE values, we introduce three reliability conditions and formulate practical guidelines for tuning the estimator parameters. We show that when the reliability conditions are met and the parameters are calibrated accordingly, the resulting effective RTE estimates accurately capture directional information flow across a broad range of scenarios. Results obtained show that the explanatory power of RTE depends sensitively on the choice of the Rényi parameter $α$. This highlights the usefulness of the RTE framework for identifying the drivers of extreme behavior in complex systems.

---

### The Optimal Sample Complexity of Linear Contracts

Authors: Mikael Møller Høgsgaard
Published: 2026-01-04
Categories: cs.GT, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2601.01496v3

In this paper, we settle the problem of learning optimal linear contracts from data in the offline setting, where agent types are drawn from an unknown distribution and the principal's goal is to design a contract that maximizes her expected utility. Specifically, our analysis shows that the simple Empirical Utility Maximization (EUM) algorithm yields an $\varepsilon$-approximation of the optimal linear contract with probability at least $1-δ$, using just $O(\ln(1/δ) / \varepsilon^2)$ samples. This result improves upon previously known bounds and matches a lower bound from Dütting et al. 2025 up to constant factors, thereby proving its optimality. Furthermore, our result establishes the stronger guarantee of uniform convergence: the empirical utility of every linear contract is an $\varepsilon$-approximation of its true expectation with probability at least $1-δ$, using the same optimal $O(\ln(1/δ) / \varepsilon^2)$ sample complexity.

---

### Accelerating Decentralized Optimization via Overlapping Local Steps

Authors: Yijie Zhou, Shi Pu
Published: 2026-01-04
Categories: cs.LG, math.OC
arXiv: https://arxiv.org/abs/2601.01493v1

Decentralized optimization has emerged as a critical paradigm for distributed learning, enabling scalable training while preserving data privacy through peer-to-peer collaboration. However, existing methods often suffer from communication bottlenecks due to frequent synchronization between nodes. We present Overlapping Local Decentralized SGD (OLDSGD), a novel approach to accelerate decentralized training by computation-communication overlapping, significantly reducing network idle time. With a deliberately designed update, OLDSGD preserves the same average update as Local SGD while avoiding communication-induced stalls. Theoretically, we establish non-asymptotic convergence rates for smooth non-convex objectives, showing that OLDSGD retains the same iteration complexity as standard Local Decentralized SGD while improving per-iteration runtime. Empirical results demonstrate OLDSGD's consistent improvements in wall-clock time convergence under different levels of communication delays. With minimal modifications to existing frameworks, OLDSGD offers a practical solution for faster decentralized learning without sacrificing theoretical guarantees.

---

### Distortion Instead of Hallucination: The Effect of Reasoning Under Strict Constraints

Authors: Junichiro Niimi
Published: 2026-01-04
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2601.01490v1

With the widespread adoption of large language models (LLMs), hallucinations, which are non-factual fabrications in model outputs, have become serious concerns. Reasoning capabilities have received attention as a self-verification process to improve output reliability. However, the effect of reasoning within a closed system where LLMs cannot rely on external tools or knowledge has yet to be clarified. We therefore conduct experiments under strict constraints (recommending peer-reviewed journal articles in computer science) to examine the effect of reasoning across multiple models (GPT-5.2 and Gemini 3 Flash). Our results reveal a problematic trade-off between constraint compliance and factual accuracy. Non-reasoning models exhibit high constraint violation rates (66-75%) but maintain factual accuracy, while reasoning models reduce violations (13-26%) but systematically distort known facts to satisfy constraints and increase complete fabrication. This trade-off pattern is consistent across both models despite different architectures, indicating a fundamental limitation of reasoning. Furthermore, reasoning does not uniformly improve output authenticity: effects diverge by model, reflecting different allocations of the compliance-truthfulness trade-off. These findings challenge the assumption that reasoning universally improves reliability: reasoning models trade honest constraint violations for detection-resistant distortions.

---

### Four Quadrants of Difficulty: A Simple Categorisation and its Limits

Authors: Vanessa Toborek, Sebastian Müller, Christian Bauckhage
Published: 2026-01-04
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2601.01488v1

Curriculum Learning (CL) aims to improve the outcome of model training by estimating the difficulty of samples and scheduling them accordingly. In NLP, difficulty is commonly approximated using task-agnostic linguistic heuristics or human intuition, implicitly assuming that these signals correlate with what neural models find difficult to learn. We propose a four-quadrant categorisation of difficulty signals -- human vs. model and task-agnostic vs. task-dependent -- and systematically analyse their interactions on a natural language understanding dataset. We find that task-agnostic features behave largely independently and that only task-dependent features align. These findings challenge common CL intuitions and highlight the need for lightweight, task-dependent difficulty estimators that better reflect model learning behaviour.

---

### DeepInv: A Novel Self-supervised Learning Approach for Fast and Accurate Diffusion Inversion

Authors: Ziyue Zhang, Luxi Lin, Xiaolin Hu, Chao Chang, HuaiXi Wang, Yiyi Zhou, Rongrong Ji
Published: 2026-01-04
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2601.01487v1

Diffusion inversion is a task of recovering the noise of an image in a diffusion model, which is vital for controllable diffusion image editing. At present, diffusion inversion still remains a challenging task due to the lack of viable supervision signals. Thus, most existing methods resort to approximation-based solutions, which however are often at the cost of performance or efficiency. To remedy these shortcomings, we propose a novel self-supervised diffusion inversion approach in this paper, termed Deep Inversion (DeepInv). Instead of requiring ground-truth noise annotations, we introduce a self-supervised objective as well as a data augmentation strategy to generate high-quality pseudo noises from real images without manual intervention. Based on these two innovative designs, DeepInv is also equipped with an iterative and multi-scale training regime to train a parameterized inversion solver, thereby achieving the fast and accurate image-to-noise mapping. To the best of our knowledge, this is the first attempt of presenting a trainable solver to predict inversion noise step by step. The extensive experiments show that our DeepInv can achieve much better performance and inference speed than the compared methods, e.g., +40.435% SSIM than EasyInv and +9887.5% speed than ReNoise on COCO dataset. Moreover, our careful designs of trainable solvers can also provide insights to the community. Codes and model parameters will be released in https://github.com/potato-kitty/DeepInv.

---

### Higher-Order Domain Generalization in Magnetic Resonance-Based Assessment of Alzheimer's Disease

Authors: Zobia Batool, Diala Lteif, Vijaya B. Kolachalama, Huseyin Ozkan, Erchan Aptoula
Published: 2026-01-04
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.01485v2

Despite progress in deep learning for Alzheimer's disease (AD) diagnostics, models trained on structural magnetic resonance imaging (sMRI) often do not perform well when applied to new cohorts due to domain shifts from varying scanners, protocols and patient demographics. AD, the primary driver of dementia, manifests through progressive cognitive and neuroanatomical changes like atrophy and ventricular expansion, making robust, generalizable classification essential for real-world use. While convolutional neural networks and transformers have advanced feature extraction via attention and fusion techniques, single-domain generalization (SDG) remains underexplored yet critical, given the fragmented nature of AD datasets. To bridge this gap, we introduce Extended MixStyle (EM), a framework for blending higher-order feature moments (skewness and kurtosis) to mimic diverse distributional variations. Trained on sMRI data from the National Alzheimer's Coordinating Center (NACC; n=4,647) to differentiate persons with normal cognition (NC) from those with mild cognitive impairment (MCI) or AD and tested on three unseen cohorts (total n=3,126), EM yields enhanced cross-domain performance, improving macro-F1 on average by 2.4 percentage points over state-of-the-art SDG benchmarks, underscoring its promise for invariant, reliable AD detection in heterogeneous real-world settings. The source code will be made available upon acceptance at https://github.com/zobia111/Extended-Mixstyle.

---

### SGD-Based Knowledge Distillation with Bayesian Teachers: Theory and Guidelines

Authors: Itai Morad, Nir Shlezinger, Yonina C. Eldar
Published: 2026-01-04
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.01484v2

Knowledge Distillation (KD) is a central paradigm for transferring knowledge from a large teacher network to a typically smaller student model, often by leveraging soft probabilistic outputs. While KD has shown strong empirical success in numerous applications, its theoretical underpinnings remain only partially understood. In this work, we adopt a Bayesian perspective on KD to rigorously analyze the convergence behavior of students trained with Stochastic Gradient Descent (SGD). We study two regimes: $(i)$ when the teacher provides the exact Bayes Class Probabilities (BCPs); and $(ii)$ supervision with noisy approximations of the BCPs. Our analysis shows that learning from BCPs yields variance reduction and removes neighborhood terms in the convergence bounds compared to one-hot supervision. We further characterize how the level of noise affects generalization and accuracy. Motivated by these insights, we advocate the use of Bayesian deep learning models, which typically provide improved estimates of the BCPs, as teachers in KD. Consistent with our analysis, we experimentally demonstrate that students distilled from Bayesian teachers not only achieve higher accuracies (up to +4.27%), but also exhibit more stable convergence (up to 30% less noise), compared to students distilled from deterministic teachers.

---

### Unified Generation and Self-Verification for Vision-Language Models via Advantage Decoupled Preference Optimization

Authors: Xinyu Qiu, Heng Jia, Zhengwen Zeng, Shuheng Shen, Changhua Meng, Yi Yang, Linchao Zhu
Published: 2026-01-04
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.01483v1

Parallel test-time scaling typically trains separate generation and verification models, incurring high training and inference costs. We propose Advantage Decoupled Preference Optimization (ADPO), a unified reinforcement learning framework that jointly learns answer generation and self-verification within a single policy. ADPO introduces two innovations: a preference verification reward improving verification capability and a decoupled optimization mechanism enabling synergistic optimization of generation and verification. Specifically, the preference verification reward computes mean verification scores from positive and negative samples as decision thresholds, providing positive feedback when prediction correctness aligns with answer correctness. Meanwhile, the advantage decoupled optimization computes separate advantages for generation and verification, applies token masks to isolate gradients, and combines masked GRPO objectives, preserving generation quality while calibrating verification scores. ADPO achieves up to +34.1% higher verification AUC and -53.5% lower inference time, with significant gains of +2.8%/+1.4% accuracy on MathVista/MMMU, +1.9 cIoU on ReasonSeg, and +1.7%/+1.0% step success rate on AndroidControl/GUI Odyssey.

---

### Robust Ship Detection and Tracking Using Modified ViBe and Backwash Cancellation Algorithm

Authors: Mohammad Hassan Saghafi, Seyed Majid Noorhosseini, Seyed Abolfazl Seyed Javadein, Hadi Khalili
Published: 2026-01-04
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.01481v1

In this paper, we propose a robust real time detection and tracking method for detecting ships in a coastal video sequences. Since coastal scenarios are unpredictable and scenes have dynamic properties it is essential to apply detection methods that are robust to these conditions. This paper presents modified ViBe for moving object detection which detects ships and backwash. In the modified ViBe the probability of losing ships is decreased in comparison with the original ViBe. It is robust to natural sea waves and variation of lights and is capable of quickly updating the background. Based on geometrical properties of ship and some concepts such as brightness distortion, a new method for backwash cancellation is proposed. Experimental results demonstrate that the proposed strategy and methods have outstanding performance in ship detection and tracking. These results also illustrate real time and precise performance of the proposed strategy.

---

### Modeling Information Blackouts in Missing Not-At-Random Time Series Data

Authors: Aman Sunesh, Allan Ma, Siddarth Nilol
Published: 2026-01-04
Categories: stat.ML, cs.LG, stat.AP
arXiv: https://arxiv.org/abs/2601.01480v3

Traffic forecasting systems rely on fixed sensor networks that frequently exhibit contiguous blackouts. Such outages are usually treated as ignorable missingness, although dropout can depend on unobserved traffic conditions. We study this possibility with an MNAR-aware latent state-space model that combines linear traffic dynamics with a Bernoulli missingness channel whose probability depends on the latent state. Inference uses an Extended Kalman Filter (EKF) followed by Rauch-Tung-Striebel (RTS) smoothing, and parameters are learned by approximate EM. We evaluate Seattle using a leakage-free, month-balanced set of 300 unique all-horizon-aligned blackout windows. On this benchmark, MAR-LDS attains 4.264 mph pooled imputation RMSE and MNAR-LDS improves it to 4.177 (difference -0.086); the detector-cluster bootstrap 95% interval is (-0.182,-0.002). A causal one-step predicted latent representation raises missingness ROC-AUC from 0.685 using observed-only features to 0.784. We further test whether this compact probabilistic model remains competitive with substantially larger neural time-series architectures under the identical masked-imputation protocol. MNAR-LDS ranks second in pooled RMSE and outperforms 8 of 9 evaluated neural architectures; it is within 1.22% of the best neural result, with no statistically resolved difference under detector-cluster bootstrap, while achieving lower P95 error, lower long-blackout RMSE, and orders of magnitude fewer stored scalar entries. MNAR roughly doubles end-to-end training time relative to MAR and increases EKF+RTS inference time by 41%, making the accuracy-complexity-cost tradeoff explicit. Controlled state-dependent blackouts further show larger gains when dropout is genuinely informative, including a 6.34% reduction in 30-minute forecast RMSE relative to MAR.

---

### Can Legislation Be Made Machine-Readable in PROLEG?

Authors: May-Myo Zin, Sabine Wehnert, Yuntao Kong, Ha-Thanh Nguyen, Wachara Fungwacharakorn, Jieying Xue, Michał Araszkiewicz, Randy Goebel, Ken Satoh, Le-Minh Nguyen
Published: 2026-01-04
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.01477v1

The anticipated positive social impact of regulatory processes requires both the accuracy and efficiency of their application. Modern artificial intelligence technologies, including natural language processing and machine-assisted reasoning, hold great promise for addressing this challenge. We present a framework to address the challenge of tools for regulatory application, based on current state-of-the-art (SOTA) methods for natural language processing (large language models or LLMs) and formalization of legal reasoning (the legal representation system PROLEG). As an example, we focus on Article 6 of the European General Data Protection Regulation (GDPR). In our framework, a single LLM prompt simultaneously transforms legal text into if-then rules and a corresponding PROLEG encoding, which are then validated and refined by legal domain experts. The final output is an executable PROLEG program that can produce human-readable explanations for instances of GDPR decisions. We describe processes to support the end-to-end transformation of a segment of a regulatory document (Article 6 from GDPR), including the prompting frame to guide an LLM to "compile" natural language text to if-then rules, then to further "compile" the vetted if-then rules to PROLEG. Finally, we produce an instance that shows the PROLEG execution. We conclude by summarizing the value of this approach and note observed limitations with suggestions to further develop such technologies for capturing and deploying regulatory frameworks.

---

### Multi-Subspace Multi-Modal Modeling for Diffusion Models: Estimation, Convergence and Mixture of Experts

Authors: Ruofeng Yang, Yongcan Li, Bo Jiang, Cheng Chen, Shuai Li
Published: 2026-01-04
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.01475v1

Recently, diffusion models have achieved a great performance with a small dataset of size $n$ and a fast optimization process. However, the estimation error of diffusion models suffers from the curse of dimensionality $n^{-1/D}$ with the data dimension $D$. Since images are usually a union of low-dimensional manifolds, current works model the data as a union of linear subspaces with Gaussian latent and achieve a $1/\sqrt{n}$ bound. Though this modeling reflects the multi-manifold property, the Gaussian latent can not capture the multi-modal property of the latent manifold. To bridge this gap, we propose the mixture subspace of low-rank mixture of Gaussian (MoLR-MoG) modeling, which models the target data as a union of $K$ linear subspaces, and each subspace admits a mixture of Gaussian latent ($n_k$ modals with dimension $d_k$). With this modeling, the corresponding score function naturally has a mixture of expert (MoE) structure, captures the multi-modal information, and contains nonlinear property. We first conduct real-world experiments to show that the generation results of MoE-latent MoG NN are much better than MoE-latent Gaussian score. Furthermore, MoE-latent MoG NN achieves a comparable performance with MoE-latent Unet with $10 \times$ parameters. These results indicate that the MoLR-MoG modeling is reasonable and suitable for real-world data. After that, based on such MoE-latent MoG score, we provide a $R^4\sqrt{Σ_{k=1}^Kn_k}\sqrt{Σ_{k=1}^Kn_kd_k}/\sqrt{n}$ estimation error, which escapes the curse of dimensionality by using data structure. Finally, we study the optimization process and prove the convergence guarantee under the MoLR-MoG modeling. Combined with these results, under a setting close to real-world data, this work explains why diffusion models only require a small training sample and enjoy a fast optimization process to achieve a great performance.

---

### Accelerating Storage-Based Training for Graph Neural Networks

Authors: Myung-Hwan Jang, Jeong-Min Park, Yunyong Ko, Sang-Wook Kim
Published: 2026-01-04
Categories: cs.LG, cs.AI, cs.DB
arXiv: https://arxiv.org/abs/2601.01473v2

Graph neural networks (GNNs) have achieved breakthroughs in various real-world downstream tasks due to their powerful expressiveness. As the scale of real-world graphs has been continuously growing, a storage-based approach to GNN training has been studied, which leverages external storage (e.g., NVMe SSDs) to handle such web-scale graphs on a single machine. Although such storage-based GNN training methods have shown promising potential in large-scale GNN training, we observed that they suffer from a severe bottleneck in data preparation since they overlook a critical challenge: how to handle a large number of small storage I/Os. To address the challenge, in this paper, we propose a novel storage-based GNN training framework, named AGNES, that employs a method of block-wise storage I/O processing to fully utilize the I/O bandwidth of high-performance storage devices. Moreover, to further enhance the efficiency of each storage I/O, AGNES employs a simple yet effective strategy, hyperbatch-based processing based on the characteristics of real-world graphs. Comprehensive experiments on five real-world graphs reveal that AGNES consistently outperforms four state-of-the-art methods, by up to 4.1X faster than the best competitor. Our code is available at https://github.com/Bigdasgit/agnes-kdd26.

---

### Double Machine Learning of Continuous Treatment Effects with Additive Instrumental Variables

Authors: Shuyuan Chen, Peng Zhang, Yifan Cui
Published: 2026-01-04
Categories: math.ST, econ.EM, stat.ME, stat.ML
arXiv: https://arxiv.org/abs/2601.01471v3

Estimating causal effects of continuous treatments is a common problem in practice, for example, in studying average dose-response functions. Classical analyses typically assume that all confounders are fully observed, whereas in real-world applications, unmeasured confounding often persists. In this article, we propose a novel framework for the identification of average dose-response functions using instrumental variables, thereby mitigating bias induced by unobserved confounders. We introduce the concept of a uniform regular weighting function and consider covering the treatment space with a finite collection of open sets. On each of these sets, such a weighting function exists, allowing us to identify the average dose-response function locally within the corresponding region. For estimation, we propose an augmented inverse probability weighted score for continuous treatments with instrumental variables under a debiased machine learning framework, and provide practical guidance for adaptively constructing regular weighting functions from the data. We also propose a falsification test for the additive instrumental variable condition and develop a testing procedure for assessing the validity of regular weighting functions. We further establish the asymptotic properties of the resulting estimators based on kernel regression or empirical risk minimization as well as the theoretical validity of the proposed testing procedures. Finally, we conduct both simulation and empirical studies to assess the finite-sample performance of the proposed methods.

---

### A construction of an optimal base for conditional attribute and attributional condition implications in triadic contexts

Authors: Romuald Kwessy Mouona, Blaise Blériot Koguep Njionou, Etienne Romuald Temgoua Alomo, Rokia Missaoui, Leonard Kwuida
Published: 2026-01-04
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.01467v1

This article studies implications in triadic contexts. Specifically, we focus on those introduced by Ganter and Obiedkov, namely conditional attribute and attributional condition implications. Our aim is to construct an optimal base for these implications.

---

### Leveraging Flatness to Improve Information-Theoretic Generalization Bounds for SGD

Authors: Ze Peng, Jian Zhang, Yisen Wang, Lei Qi, Yinghuan Shi, Yang Gao
Published: 2026-01-04
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.01465v1

Information-theoretic (IT) generalization bounds have been used to study the generalization of learning algorithms. These bounds are intrinsically data- and algorithm-dependent so that one can exploit the properties of data and algorithm to derive tighter bounds. However, we observe that although the flatness bias is crucial for SGD's generalization, these bounds fail to capture the improved generalization under better flatness and are also numerically loose. This is caused by the inadequate leverage of SGD's flatness bias in existing IT bounds. This paper derives a more flatness-leveraging IT bound for the flatness-favoring SGD. The bound indicates the learned models generalize better if the large-variance directions of the final weight covariance have small local curvatures in the loss landscape. Experiments on deep neural networks show our bound not only correctly reflects the better generalization when flatness is improved, but is also numerically much tighter. This is achieved by a flexible technique called "omniscient trajectory". When applied to Gradient Descent's minimax excess risk on convex-Lipschitz-Bounded problems, it improves representative IT bounds' $Ω(1)$ rates to $O(1/\sqrt{n})$. It also implies a by-pass of memorization-generalization trade-offs.

---

### Bridging the gap: A comparative exploration of Speech-LLM and end-to-end architecture for multilingual conversational ASR

Authors: Yuxiang Mei, Dongxing Xu, Jiaen Liang, Yanhua Long
Published: 2026-01-04
Categories: cs.CL, cs.SD, eess.AS
arXiv: https://arxiv.org/abs/2601.01461v3

The INTERSPEECH 2025 Challenge on Multilingual Conversational Speech Language Models (MLC-SLM) promotes multilingual conversational ASR with large language models (LLMs). Our previous SHNU-mASR system adopted a competitive parallel-speech-encoder architecture that integrated Whisper and mHuBERT with an LLM. However, it faced two challenges: simple feature concatenation may not fully exploit complementary information, and the performance gap between LLM-based ASR and end-to-end(E2E) encoder-decoder ASR remained unexplored. In this work, we present an enhanced LLM-based ASR framework that combines fine-tuned Whisper and mHuBERT encoders with an LLM to enrich speech representations. We first evaluate E2E Whisper models with LoRA and full fine-tuning on the MLC-SLM ASR task, and then propose cross-attention-based fusion mechanisms for the parallel-speech-encoder. On the official evaluation set of the MLC-SLM Challenge, our system achieves a CER/WER of 10.69%, ranking on par with the top-ranked Track 1 systems, even though it uses only 1,500 hours of baseline training data compared with their large-scale training sets. Nonetheless, we find that our final LLM-based ASR still does not match the performance of a fine-tuned E2E Whisper model, providing valuable empirical guidance for future Speech-LLM design. Our code is publicly available at https://github.com/1535176727/MLC-SLM.

---

### Domain Adaptation of Carotid Ultrasound Images using Generative Adversarial Network

Authors: Mohd Usama, Belal Ahmad, Christer Gronlund, Faleh Menawer R Althiyabi
Published: 2026-01-04
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.01460v1

Deep learning has been extensively used in medical imaging applications, assuming that the test and training datasets belong to the same probability distribution. However, a common challenge arises when working with medical images generated by different systems or even the same system with different parameter settings. Such images contain diverse textures and reverberation noise that violate the aforementioned assumption. Consequently, models trained on data from one device or setting often struggle to perform effectively with data from other devices or settings. In addition, retraining models for each specific device or setting is labor-intensive and costly. To address these issues in ultrasound images, we propose a novel Generative Adversarial Network (GAN)-based model. We formulated the domain adaptation tasks as an image-to-image translation task, in which we modified the texture patterns and removed reverberation noise in the test data images from the source domain to align with those in the target domain images while keeping the image content unchanged. We applied the proposed method to two datasets containing carotid ultrasound images from three different domains. The experimental results demonstrate that the model successfully translated the texture pattern of images and removed reverberation noise from the ultrasound images. Furthermore, we evaluated the CycleGAN approaches for a comparative study with the proposed model. The experimental findings conclusively demonstrated that the proposed model achieved domain adaptation (histogram correlation (0.960 (0.019), & 0.920 (0.043) and bhattacharya distance (0.040 (0.020), & 0.085 (0.048)), compared to no adaptation (0.916 (0.062) & 0.890 (0.077), 0.090 (0.070) & 0.121 (0.095)) for both datasets.

---

### Language as Prior, Vision as Calibration: Metric Scale Recovery for Monocular Depth Estimation

Authors: Mingxia Zhan, Li Zhang, Beibei Wang, Yingjie Wang, Zenglin Shi
Published: 2026-01-04
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.01457v3

Relative-depth foundation models transfer well, yet monocular metric depth remains ill-posed due to unidentifiable global scale and heightened domain-shift sensitivity. Under a frozen-backbone calibration setting, we recover metric depth via an image-specific affine transform in inverse depth and train only lightweight calibration heads while keeping the relative-depth backbone and the CLIP text encoder fixed. Since captions provide coarse but noisy scale cues that vary with phrasing and missing objects, we use language to predict an uncertainty-aware envelope that bounds feasible calibration parameters in an unconstrained space, rather than committing to a text-only point estimate. We then use pooled multi-scale frozen visual features to select an image-specific calibration within this envelope. During training, a closed-form least-squares oracle in inverse depth provides per-image supervision for learning the envelope and the selected calibration. Experiments on NYUv2 and KITTI improve in-domain accuracy, while zero-shot transfer to SUN-RGBD and DDAD demonstrates improved robustness over strong language-only baselines.

---

### Rethinking Multimodal Few-Shot 3D Point Cloud Segmentation: From Fused Refinement to Decoupled Arbitration

Authors: Wentao Bian, Fenglei Xu
Published: 2026-01-04
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2601.01456v2

In this paper, we revisit multimodal few-shot 3D point cloud semantic segmentation (FS-PCS), identifying a conflict in "Fuse-then-Refine" paradigms: the "Plasticity-Stability Dilemma." In addition, CLIP's inter-class confusion can result in semantic blindness. To address these issues, we present the Decoupled-experts Arbitration Few-Shot SegNet (DA-FSS), a model that effectively distinguishes between semantic and geometric paths and mutually regularizes their gradients to achieve better generalization. DA-FSS employs the same backbone and pre-trained text encoder as MM-FSS to generate text embeddings, which can increase free modalities' utilization rate and better leverage each modality's information space. To achieve this, we propose a Parallel Expert Refinement module to generate each modal correlation. We also propose a Stacked Arbitration Module (SAM) to perform convolutional fusion and arbitrate correlations for each modality pathway. The Parallel Experts decouple two paths: a Geometric Expert maintains plasticity, and a Semantic Expert ensures stability. They are coordinated via a Decoupled Alignment Module (DAM) that transfers knowledge without propagating confusion. Experiments on popular datasets (S3DIS, ScanNet) demonstrate the superiority of DA-FSS over MM-FSS. Meanwhile, geometric boundaries, completeness, and texture differentiation are all superior to the baseline. The code is available at: https://github.com/MoWenQAQ/DA-FSS/.

---

### PartImageNet++ Dataset: Enhancing Visual Models with High-Quality Part Annotations

Authors: Xiao Li, Zilong Liu, Yining Liu, Zhuhong Li, Na Dong, Sitian Qin, Xiaolin Hu
Published: 2026-01-04
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.01454v1

To address the scarcity of high-quality part annotations in existing datasets, we introduce PartImageNet++ (PIN++), a dataset that provides detailed part annotations for all categories in ImageNet-1K. With 100 annotated images per category, totaling 100K images, PIN++ represents the most comprehensive dataset covering a diverse range of object categories. Leveraging PIN++, we propose a Multi-scale Part-supervised recognition Model (MPM) for robust classification on ImageNet-1K. We first trained a part segmentation network using PIN++ and used it to generate pseudo part labels for the remaining unannotated images. MPM then integrated a conventional recognition architecture with auxiliary bypass layers, jointly supervised by both pseudo part labels and the original part annotations. Furthermore, we conducted extensive experiments on PIN++, including part segmentation, object segmentation, and few-shot learning, exploring various ways to leverage part annotations in downstream tasks. Experimental results demonstrated that our approach not only enhanced part-based models for robust object recognition but also established strong baselines for multiple downstream tasks, highlighting the potential of part annotations in improving model performance. The dataset and the code are available at https://github.com/LixiaoTHU/PartImageNetPP.

---

### Robust and Efficient Zeroth-Order LLM Fine-Tuning via Adaptive Bayesian Subspace Optimizer

Authors: Jian Feng, Zhihong Huang
Published: 2026-01-04
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.01452v4

Fine-tuning large language models (LLMs) with zeroth-order (ZO) optimization reduces memory by approximating gradients through function evaluations. However, existing methods essentially perform updates in a one-dimensional space, and suffer from collapse or substantial performance degradation under low-precision training. We introduce BSZO, an adaptive \textbf{B}ayesian \textbf{S}ubspace \textbf{Z}eroth-Order \textbf{O}ptimizer, which applies Kalman filtering to combine finite-difference information across multiple perturbation directions within a subspace. By treating each finite-difference measurement as a noisy observation, BSZO builds a posterior distribution over the subspace-projected gradient and updates it through Bayesian inference, with a residual-based adaptive mechanism to adapt to noise variations. Theoretical analysis shows that BSZO improves the convergence rate by a factor of $k/γ$ compared to standard ZO methods. Experiments on RoBERTa, Mistral, and OPT models show that BSZO outperforms the baselines across various tasks, achieving up to 6.67\% absolute average improvement on OPT-13B while remaining robust under fp16/bf16 precision and keeping memory usage close to inference-only baselines (1.00$\times$--1.08$\times$ of MeZO).

---

### Segmentation and Processing of German Court Decisions from Open Legal Data

Authors: Harshil Darji, Martin Heckelmann, Christina Kratsch, Gerard de Melo
Published: 2026-01-04
Categories: cs.CL, cs.IR, cs.LG
arXiv: https://arxiv.org/abs/2601.01449v1

The availability of structured legal data is important for advancing Natural Language Processing (NLP) techniques for the German legal system. One of the most widely used datasets, Open Legal Data, provides a large-scale collection of German court decisions. While the metadata in this raw dataset is consistently structured, the decision texts themselves are inconsistently formatted and often lack clearly marked sections. Reliable separation of these sections is important not only for rhetorical role classification but also for downstream tasks such as retrieval and citation analysis. In this work, we introduce a cleaned and sectioned dataset of 251,038 German court decisions derived from the official Open Legal Data dataset. We systematically separated three important sections in German court decisions, namely Tenor (operative part of the decision), Tatbestand (facts of the case), and Entscheidungsgründe (judicial reasoning), which are often inconsistently represented in the original dataset. To ensure the reliability of our extraction process, we used Cochran's formula with a 95% confidence level and a 5% margin of error to draw a statistically representative random sample of 384 cases, and manually verified that all three sections were correctly identified. We also extracted the Rechtsmittelbelehrung (appeal notice) as a separate field, since it is a procedural instruction and not part of the decision itself. The resulting corpus is publicly available in the JSONL format, making it an accessible resource for further research on the German legal system.

---

### iFlip: Iterative Feedback-driven Counterfactual Example Refinement

Authors: Yilong Wang, Qianli Wang, Nils Feldhus
Published: 2026-01-04
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2601.01446v2

Counterfactual examples are minimal edits to an input that alter a model's prediction. They are widely employed in explainable AI to probe model behavior and in natural language processing (NLP) to augment training data. However, generating valid counterfactuals with large language models (LLMs) remains challenging, as existing single-pass methods often fail to induce reliable label changes, neglecting LLMs' self-correction capabilities. To explore this untapped potential, we propose iFlip, an iterative refinement approach that leverages three types of feedback, including model confidence, feature attribution, and natural language. Our results show that iFlip achieves an average 57.8% higher validity than the five state-of-the-art baselines, as measured by the label flipping rate. The user study further corroborates that iFlip outperforms baselines in completeness, overall satisfaction, and feasibility. In addition, ablation studies demonstrate that three components are paramount for iFlip to generate valid counterfactuals: leveraging an appropriate number of iterations, pointing to highly attributed words, and early stopping. Finally, counterfactuals generated by iFlip enable effective counterfactual data augmentation, substantially improving model performance and robustness.

---

### Fast Gibbs Sampling on Bayesian Hidden Markov Model with Missing Observations

Authors: Dongrong Li, Tianwei Yu, Xiaodan Fan
Published: 2026-01-04
Categories: stat.ML, cs.LG, stat.ME
arXiv: https://arxiv.org/abs/2601.01442v1

The Hidden Markov Model (HMM) is a widely-used statistical model for handling sequential data. However, the presence of missing observations in real-world datasets often complicates the application of the model. The EM algorithm and Gibbs samplers can be used to estimate the model, yet suffering from various problems including non-convexity, high computational complexity and slow mixing. In this paper, we propose a collapsed Gibbs sampler that efficiently samples from HMMs' posterior by integrating out both the missing observations and the corresponding latent states. The proposed sampler is fast due to its three advantages. First, it achieves an estimation accuracy that is comparable to existing methods. Second, it can produce a larger Effective Sample Size (ESS) per iteration, which can be justified theoretically and numerically. Third, when the number of missing entries is large, the sampler has a significant smaller computational complexity per iteration compared to other methods, thus is faster computationally. In summary, the proposed sampling algorithm is fast both computationally and theoretically and is particularly advantageous when there are a lot of missing entries. Finally, empirical evaluations based on numerical simulations and real data analysis demonstrate that the proposed algorithm consistently outperforms existing algorithms in terms of time complexity and sampling efficiency (measured in ESS).

---

### Image Synthesis Using Spintronic Deep Convolutional Generative Adversarial Network

Authors: Saumya Gupta, Abhinandan, Venkatesh vadde, Bhaskaran Muralidharan, Abhishek Sharma
Published: 2026-01-04
Categories: physics.app-ph, cs.CV
arXiv: https://arxiv.org/abs/2601.01441v1

The computational requirements of generative adversarial networks (GANs) exceed the limit of conventional Von Neumann architectures, necessitating energy efficient alternatives such as neuromorphic spintronics. This work presents a hybrid CMOS-spintronic deep convolutional generative adversarial network (DCGAN) architecture for synthetic image generation. The proposed generative vision model approach follows the standard framework, leveraging generator and discriminators adversarial training with our designed spintronics hardware for deconvolution, convolution, and activation layers of the DCGAN architecture. To enable hardware aware spintronic implementation, the generator's deconvolution layers are restructured as zero padded convolution, allowing seamless integration with a 6-bit skyrmion based synapse in a crossbar, without compromising training performance. Nonlinear activation functions are implemented using a hybrid CMOS domain wall based Rectified linear unit (ReLU) and Leaky ReLU units. Our proposed tunable Leaky ReLU employs domain wall position coded, continuous resistance states and a piecewise uniaxial parabolic anisotropy profile with a parallel MTJ readout, exhibiting energy consumption of 0.192 pJ. Our spintronic DCGAN model demonstrates adaptability across both grayscale and colored datasets, achieving Fr'echet Inception Distances (FID) of 27.5 for the Fashion MNIST and 45.4 for Anime Face datasets, with testing energy (training energy) of 4.9 nJ (14.97~nJ/image) and 24.72 nJ (74.7 nJ/image).

---

### In defense of the two-stage framework for open-set domain adaptive semantic segmentation

Authors: Wenqi Ren, Weijie Wang, Meng Zheng, Ziyan Wu, Yang Tang, Zhun Zhong, Nicu Sebe
Published: 2026-01-04
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.01439v1

Open-Set Domain Adaptation for Semantic Segmentation (OSDA-SS) presents a significant challenge, as it requires both domain adaptation for known classes and the distinction of unknowns. Existing methods attempt to address both tasks within a single unified stage. We question this design, as the annotation imbalance between known and unknown classes often leads to negative transfer of known classes and underfitting for unknowns. To overcome these issues, we propose SATS, a Separating-then-Adapting Training Strategy, which addresses OSDA-SS through two sequential steps: known/unknown separation and unknown-aware domain adaptation. By providing the model with more accurate and well-aligned unknown classes, our method ensures a balanced learning of discriminative features for both known and unknown classes, steering the model toward discovering truly unknown objects. Additionally, we present hard unknown exploration, an innovative data augmentation method that exposes the model to more challenging unknowns, strengthening its ability to capture more comprehensive understanding of target unknowns. We evaluate our method on public OSDA-SS benchmarks. Experimental results demonstrate that our method achieves a substantial advancement, with a +3.85% H-Score improvement for GTA5-to-Cityscapes and +18.64% for SYNTHIA-to-Cityscapes, outperforming previous state-of-the-art methods.

---

### Online Estimation and Manipulation of Articulated Objects

Authors: Russell Buchanan, Adrian Röfer, João Moura, Abhinav Valada, Sethu Vijayakumar
Published: 2026-01-04
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2601.01438v1

From refrigerators to kitchen drawers, humans interact with articulated objects effortlessly every day while completing household chores. For automating these tasks, service robots must be capable of manipulating arbitrary articulated objects. Recent deep learning methods have been shown to predict valuable priors on the affordance of articulated objects from vision. In contrast, many other works estimate object articulations by observing the articulation motion, but this requires the robot to already be capable of manipulating the object. In this article, we propose a novel approach combining these methods by using a factor graph for online estimation of articulation which fuses learned visual priors and proprioceptive sensing during interaction into an analytical model of articulation based on Screw Theory. With our method, a robotic system makes an initial prediction of articulation from vision before touching the object, and then quickly updates the estimate from kinematic and force sensing during manipulation. We evaluate our method extensively in both simulations and real-world robotic manipulation experiments. We demonstrate several closed-loop estimation and manipulation experiments in which the robot was capable of opening previously unseen drawers. In real hardware experiments, the robot achieved a 75% success rate for autonomous opening of unknown articulated objects.

---

### Personalizing black-box models for nonparametric regression with minimax optimality

Authors: Sai Li, Linjun Zhang
Published: 2026-01-04
Categories: stat.ME, stat.ML
arXiv: https://arxiv.org/abs/2601.01432v1

Recent advances in large-scale models, including deep neural networks and large language models, have substantially improved performance across a wide range of learning tasks. The widespread availability of such pre-trained models creates new opportunities for data-efficient statistical learning, provided they can be effectively integrated into downstream tasks. Motivated by this setting, we study few-shot personalization, where a pre-trained black-box model is adapted to a target domain using a limited number of samples. We develop a theoretical framework for few-shot personalization in nonparametric regression and propose algorithms that can incorporate a black-box pre-trained model into the regression procedure. We establish the minimax optimal rate for the personalization problem and show that the proposed method attains this rate. Our results clarify the statistical benefits of leveraging pre-trained models under sample scarcity and provide robustness guarantees when the pre-trained model is not informative. We illustrate the finite-sample performance of the methods through simulations and an application to the California housing dataset with several pre-trained models.

---

### EdgeNeRF: Edge-Guided Regularization for Neural Radiance Fields from Sparse Views

Authors: Weiqi Yu, Yiyang Yao, Lin He, Jianming Lv
Published: 2026-01-04
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.01431v1

Neural Radiance Fields (NeRF) achieve remarkable performance in dense multi-view scenarios, but their reconstruction quality degrades significantly under sparse inputs due to geometric artifacts. Existing methods utilize global depth regularization to mitigate artifacts, leading to the loss of geometric boundary details. To address this problem, we propose EdgeNeRF, an edge-guided sparse-view 3D reconstruction algorithm. Our method leverages the prior that abrupt changes in depth and normals generate edges. Specifically, we first extract edges from input images, then apply depth and normal regularization constraints to non-edge regions, enhancing geometric consistency while preserving high-frequency details at boundaries. Experiments on LLFF and DTU datasets demonstrate EdgeNeRF's superior performance, particularly in retaining sharp geometric boundaries and suppressing artifacts. Additionally, the proposed edge-guided depth regularization module can be seamlessly integrated into other methods in a plug-and-play manner, significantly improving their performance without substantially increasing training time. Code is available at https://github.com/skyhigh404/edgenerf.

---

### SWE-Lego: Pushing the Limits of Supervised Fine-tuning for Software Issue Resolving

Authors: Chaofan Tao, Jierun Chen, Yuxin Jiang, Kaiqi Kou, Shaowei Wang, Ruoyu Wang, Xiaohui Li, Sidi Yang, Yiming Du, Jianbo Dai, Zhiming Mao, Xinyu Wang et al.
Published: 2026-01-04
Categories: cs.SE, cs.CL
arXiv: https://arxiv.org/abs/2601.01426v2

We present SWE-Lego, a supervised fine-tuning (SFT) recipe designed to achieve state-ofthe-art performance in software engineering (SWE) issue resolving. In contrast to prevalent methods that rely on complex training paradigms (e.g., mid-training, SFT, reinforcement learning, and their combinations), we explore how to push the limits of a lightweight SFT-only approach for SWE tasks. SWE-Lego comprises three core building blocks, with key findings summarized as follows: 1) the SWE-Lego dataset, a collection of 32k highquality task instances and 18k validated trajectories, combining real and synthetic data to complement each other in both quality and quantity; 2) a refined SFT procedure with error masking and a difficulty-based curriculum, which demonstrably improves action quality and overall performance. Empirical results show that with these two building bricks alone,the SFT can push SWE-Lego models to state-of-the-art performance among open-source models of comparable size on SWE-bench Verified: SWE-Lego-Qwen3-8B reaches 42.2%, and SWE-Lego-Qwen3-32B attains 52.6%. 3) We further evaluate and improve test-time scaling (TTS) built upon the SFT foundation. Based on a well-trained verifier, SWE-Lego models can be significantly boosted--for example, 42.2% to 49.6% and 52.6% to 58.8% under TTS@16 for the 8B and 32B models, respectively.

---

### DreamID-V:Bridging the Image-to-Video Gap for High-Fidelity Face Swapping via Diffusion Transformer

Authors: Xu Guo, Fulong Ye, Xinghui Li, Pengqi Tu, Pengze Zhang, Qichao Sun, Songtao Zhao, Xiangwang Hou, Qian He
Published: 2026-01-04
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.01425v1

Video Face Swapping (VFS) requires seamlessly injecting a source identity into a target video while meticulously preserving the original pose, expression, lighting, background, and dynamic information. Existing methods struggle to maintain identity similarity and attribute preservation while preserving temporal consistency. To address the challenge, we propose a comprehensive framework to seamlessly transfer the superiority of Image Face Swapping (IFS) to the video domain. We first introduce a novel data pipeline SyncID-Pipe that pre-trains an Identity-Anchored Video Synthesizer and combines it with IFS models to construct bidirectional ID quadruplets for explicit supervision. Building upon paired data, we propose the first Diffusion Transformer-based framework DreamID-V, employing a core Modality-Aware Conditioning module to discriminatively inject multi-model conditions. Meanwhile, we propose a Synthetic-to-Real Curriculum mechanism and an Identity-Coherence Reinforcement Learning strategy to enhance visual realism and identity consistency under challenging scenarios. To address the issue of limited benchmarks, we introduce IDBench-V, a comprehensive benchmark encompassing diverse scenes. Extensive experiments demonstrate DreamID-V outperforms state-of-the-art methods and further exhibits exceptional versatility, which can be seamlessly adapted to various swap-related tasks.

---

### Unveiling the Heart-Brain Connection: An Analysis of ECG in Cognitive Performance

Authors: Akshay Sasi, Malavika Pradeep, Nusaibah Farrukh, Rahul Venugopal, Elizabeth Sherly
Published: 2026-01-04
Categories: cs.LG, q-bio.NC
arXiv: https://arxiv.org/abs/2601.01424v1

Understanding the interaction of neural and cardiac systems during cognitive activity is critical to advancing physiological computing. Although EEG has been the gold standard for assessing mental workload, its limited portability restricts its real-world use. Widely available ECG through wearable devices proposes a pragmatic alternative. This research investigates whether ECG signals can reliably reflect cognitive load and serve as proxies for EEG-based indicators. In this work, we present multimodal data acquired from two different paradigms involving working-memory and passive-listening tasks. For each modality, we extracted ECG time-domain HRV metrics and Catch22 descriptors against EEG spectral and Catch22 features, respectively. We propose a cross-modal XGBoost framework to project the ECG features onto EEG-representative cognitive spaces, thereby allowing workload inferences using only ECG. Our results show that ECG-derived projections expressively capture variation in cognitive states and provide good support for accurate classification. Our findings underpin ECG as an interpretable, real-time, wearable solution for everyday cognitive monitoring.

---

### A Depth Hierarchy for Computing the Maximum in ReLU Networks via Extremal Graph Theory

Authors: Itay Safran
Published: 2026-01-04
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.01417v1

We consider the problem of exact computation of the maximum function over $d$ real inputs using ReLU neural networks. We prove a depth hierarchy, wherein width $Ω\big(d^{1+\frac{1}{2^{k-2}-1}}\big)$ is necessary to represent the maximum for any depth $3\le k\le \log_2(\log_2(d))$. This is the first unconditional super-linear lower bound for this fundamental operator at depths $k\ge3$, and it holds even if the depth scales with $d$. Our proof technique is based on a combinatorial argument and associates the non-differentiable ridges of the maximum with cliques in a graph induced by the first hidden layer of the computing network, utilizing Turán's theorem from extremal graph theory to show that a sufficiently narrow network cannot capture the non-linearities of the maximum. This suggests that despite its simple nature, the maximum function possesses an inherent complexity that stems from the geometric structure of its non-differentiable hyperplanes, and provides a novel approach for proving lower bounds for deep neural networks.

---