# Research Papers — 2026-01 · bundle page 180 of 189

> Full-text markdown of papers #8951–9000 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/180
[← Previous bundle](https://aipod.dev/papers/archive/2026-01/page/179.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-01/page/181.md)

### L2CU: Learning to Complement Unseen Users

Authors: Dileepa Pitawela, Gustavo Carneiro, Hsiang-Ting Chen
Published: 2026-01-03
Categories: cs.LG, cs.AI, cs.HC
arXiv: https://arxiv.org/abs/2601.06119v1

Recent research highlights the potential of machine learning models to learn to complement (L2C) human strengths; however, generalizing this capability to unseen users remains a significant challenge. Existing L2C methods oversimplify interaction between human and AI by relying on a single, global user model that neglects individual user variability, leading to suboptimal cooperative performance. Addressing this, we introduce L2CU, a novel L2C framework for human-AI cooperative classification with unseen users. Given sparse and noisy user annotations, L2CU identifies representative annotator profiles capturing distinct labeling patterns. By matching unseen users to these profiles, L2CU leverages profile-specific models to complement the user and achieve superior joint accuracy. We evaluate L2CU on datasets (CIFAR-10N, CIFAR-10H, Fashion-MNIST-H, Chaoyang and AgNews), demonstrating its effectiveness as a model-agnostic solution for improving human-AI cooperative classification.

---

### Beyond Reproducibility: Token Probabilities Expose Large Language Model Nondeterminism

Authors: Tairan Fu, Gonzalo Martínez, Javier Conde, Carlos Arriaga, Pedro Reviriego, Xiuyuan Qi, Shanshan Liu
Published: 2026-01-03
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.06118v1

The execution of Large Language Models (LLMs) has been shown to produce nondeterministic results when run on Graphics Processing Units (GPUs), even when they are configured to produce deterministic results. This is due to the finite precision effects of the arithmetic operations, which depend on the order in which they are executed. This order, in turn, depends on the processes that are running concurrently on the GPU. Previous studies have focused on the impact of nondeterminism on the text generated by the LLMs or on proposing mechanisms to achieve deterministic execution. This work takes a closer look at nondeterminism by analyzing the variations on the token probabilities, not on the generated text. Interestingly, all the models evaluated have similar results in both the trends and the actual values of the variations of the probabilities. In particular, the results show that the effects of nondeterminism are significant for token probabilities that are in the range of 0.1 to 0.9, while they are much smaller when the probabilities are close to 0 or 1. This has significant implications for our understanding of nondeterminism. The first is that nondeterminism will likely have a non-negligible impact on generated text when the temperature is not zero, as it introduces significant variations in the token probabilities except when they are close to 0 or 1. Secondly, it suggests that all models have similar non deterministic variations at the token probability level. Therefore, different variations in the performance of the generated text, for example, when measuring accuracy on a benchmark, seem to come from different token probabilities or response lengths. A third implication is that we may be able to estimate the impact of nondeterminism by running a single inference and analyzing the token level probabilities, instead of having to run the same inference many times.

---

### The Active Discoverer Framework: Towards Autonomous Physics Reasoning through Neuro-Symbolic LaTeX Synthesis

Authors: Hyunjun Jeon
Published: 2026-01-03
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.06117v3

Modern artificial intelligence excels at statistical interpolation within seen manifolds but fundamentally fails at the exact reasoning required for theoretical physics and mathematics. We identify the "Float Wall" -- a catastrophic collapse of neural extrapolation at scales beyond $10^{16}$ -- caused by standard floating-point representation and linguistic tokenization (BPE). To resolve this, we introduce the Active Discoverer Framework, a digit-native neuro-symbolic architecture designed for invariant discovery. At its core is NumberNet, a Siamese Arithmetic Transformer that utilizes least-significant-bit (LSB) sequence encoding to achieve 0% precision loss and cosmic-scale extrapolation up to $10^{50}$. To enforce physical grounding, we implement a Hamiltonian-based energy descent and Symmetry Grouping layer, ensuring the model respects Noether's theorem natively. The primary innovation is the Symbolic LaTeX Bottleneck: an active discovery loop where the model is forced to hypothesize unknown physical variables through an autoregressive LaTeX decoder. By reconciling numeric "hallucinations" with structurally valid mathematical expressions, the framework ensures that any discovered physics is parsimonious and human-interpretable. We evaluate this system against a 30-billion scale benchmark and the Universal Physics Pantheon, featuring 50 "Chaos Mode" systemic perturbations. Our results demonstrate that while traditional GBDT and LLM-based architectures collapse at cosmic scales, the Active Discoverer autonomously deduces universal constants such as the Gravitational Constant ($G$) with high fidelity. This framework establishes a path toward zero-hallucination artificial intelligence and truly autonomous scientific research agents.

---

### The Homogenization Problem in LLMs: Towards Meaningful Diversity in AI Safety

Authors: Ian Rios-Sialer
Published: 2026-01-03
Categories: cs.AI, cs.CL, cs.CY
arXiv: https://arxiv.org/abs/2601.06116v7

Generative AI models reproduce the human biases in their training data and further amplify them through mechanisms such as mode collapse. The loss of diversity produces homogenization, which not only harms the minoritized but impoverishes everyone. We argue homogenization should be a central concern in AI safety. To meaningfully characterize homogenization in Large Language Models (LLMs), we introduce a framework that allows stakeholders to encode their context and value system. We illustrate our approach with an experiment that surfaces gender bias in an LLM (Claude 3.5 Haiku) on an open-ended story prompt. Building from queer theory, we formalize homogenization in terms of normativity. Borrowing language from feminist theory, we introduce the concept of xeno-reproduction as a class of tasks for mitigating homogenization by promoting diversity. Our work opens a collaborative line of research that seeks to understand and advance diversity in AI.

---

### Dreaming Is Not a Bug: A Jung-Inspired Dream Layer for Multi-Agent LLM Companions

Authors: V. Cheung
Published: 2026-01-03
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.06115v1

Inspired by a personal dream about knowledge-sharing barriers in an everyday hardware project, this paper proposes a Jung-inspired "Dream Layer" for LLM companions, reframing controlled offline hallucinations as a resource for learning and relationship-building rather than a mere reliability bug. Drawing on Jung's notion of the collective unconscious as a shared repository of archetypal forms, we introduce an Artificial Collective Unconscious (ACU): a shared dream pool where agents contribute de-identified, abstract Interaction Templates that are later re-instantiated as idiosyncratic Dream Narratives. The Dream Layer runs strictly offline: logic-enforcing modules are relaxed and sampling temperature is increased, yielding safe but deliberately bizarre narratives (e.g., travel sequences with mismatched currencies) that augment data for rare events and edge-case safety tests; to harness risk productively, we add a governance stack of strict abstraction, temporal delays, and ephemeral memory. Through behavioural simulations of everyday dialogue and long-horizon adaptation tasks, we show that the Dream Layer enables a critical decoupling: agents remain firm on safety constraints (e.g., security policies) while becoming flexible in narrative strategy (e.g., using shared archetypal metaphors to resolve deadlocks), conceptually reframing hallucination so that online, unmarked instances remain bugs, whereas bounded, marked, and delayed ones become a goldmine for synthetic scenarios and deepened companionship, echoing anti-overfitting dream mechanisms proposed in contemporary neuroscience.

---

### GroupSegment-SHAP: Shapley Value Explanations with Group-Segment Players for Multivariate Time Series

Authors: Jinwoong Kim, Sangjin Park
Published: 2026-01-03
Categories: cs.LG, cs.AI, cs.GT
arXiv: https://arxiv.org/abs/2601.06114v2

Multivariate time-series models achieve strong predictive performance in healthcare, industry, energy, and finance, but how they combine cross-variable interactions with temporal dynamics remains unclear. SHapley Additive exPlanations (SHAP) are widely used for interpretation. However, existing time-series variants typically treat the feature and time axes independently, fragmenting structural signals formed jointly by multiple variables over specific intervals. We propose GroupSegment SHAP (GS-SHAP), which constructs explanatory units as group-segment players based on cross-variable dependence and distribution shifts over time, and then quantifies each unit's contribution via Shapley attribution. We evaluate GS-SHAP across four real-world domains: human activity recognition, power-system forecasting, medical signal analysis, and financial time series, and compare it with KernelSHAP, TimeSHAP, SequenceSHAP, WindowSHAP, and TSHAP. GS-SHAP improves deletion-based faithfulness (DeltaAUC) by about 1.7x on average over time-series SHAP baselines, while reducing wall-clock runtime by about 40 percent on average under matched perturbation budgets. A financial case study shows that GS-SHAP identifies interpretable multivariate-temporal interactions among key market variables during high-volatility regimes.

---

### Towards Infinite Length Extrapolation: A Unified Approach

Authors: Nitin Vetcha
Published: 2026-01-03
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.06113v1

Large language models (LLMs) have revolutionized natural language processing, but their ability to process long sequences is fundamentally limited by the context window size during training. Existing length extrapolation methods often suffer from performance degradation or computational inefficiencies. We thereby use a unified framework that reinterprets positional encoding methods as a decomposition of the attention score into a multiplicative transformation and an additive bias. This perspective not only subsumes popular approaches such as relative position embeddings and attention-bias moderated approaches but also exposes their inherent limitations in handling long-range dependencies. To address these shortcomings, motivated by our framework, we introduce Adaptive Positional Encoding (APE), which leverages adaptive frequency modulation and an intricately designed decay bias that incorporates linear, logarithmic, and square-root terms. Our theoretical analysis establishes conditions for infinite-context extrapolation, ensuring that the softmax normalization remains well-defined over unbounded sequences while preserving long-distance correlations, entropy boundedness and gradient positional sensitivity. We substantiate our claims with an experimental case study on TinyStories dataset as well as a new synthetic dataset, \emph{Long Tiny Stories} featuring stories up to 32,000 words. Relevant code, dataset and model weights are available at https://anonymous.4open.science/r/Check-2DAD/.

---

### ReliabilityBench: Evaluating LLM Agent Reliability Under Production-Like Stress Conditions

Authors: Aayush Gupta
Published: 2026-01-03
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.06112v1

Existing benchmarks for tool-using LLM agents primarily report single-run success rates and miss reliability properties required in production. We introduce \textbf{ReliabilityBench}, a benchmark for evaluating agent reliability across three dimensions: (i) consistency under repeated execution using $\mathrm{pass}^k$, (ii) robustness to semantically equivalent task perturbations at intensity $ε$, and (iii) fault tolerance under controlled tool/API failures at intensity $λ$. ReliabilityBench contributes a unified reliability surface $R(k,ε,λ)$, \textit{action metamorphic relations} that define correctness via end-state equivalence rather than text similarity, and a chaos-engineering-style fault injection framework (timeouts, rate limits, partial responses, schema drift). We evaluate two models (Gemini 2.0 Flash, GPT-4o) and two agent architectures (ReAct, Reflexion) across four domains (scheduling, travel, customer support, e-commerce) over 1,280 episodes. Perturbations alone reduce success from 96.9% at $ε=0$ to 88.1% at $ε=0.2$. Rate limiting is the most damaging fault in ablations. ReAct is more robust than Reflexion under combined stress, and Gemini 2.0 Flash achieves comparable reliability to GPT-4o at much lower cost. ReliabilityBench provides a systematic framework for assessing production readiness of LLM agents.

---

### LLM Powered Social Digital Twins: A Framework for Simulating Population Behavioral Response to Policy Interventions

Authors: Fatima Koaik, Aayush Gupta, Farahan Raza Sheikh
Published: 2026-01-03
Categories: cs.AI, cs.CY
arXiv: https://arxiv.org/abs/2601.06111v2

Predicting how populations respond to policy interventions is a fundamental challenge in computational social science and public policy. Traditional approaches rely on aggregate statistical models that capture historical correlations but lack mechanistic interpretability and struggle with novel policy scenarios. We present a general framework for constructing Social Digital Twins - virtual population replicas where Large Language Models (LLMs) serve as cognitive engines for individual agents. Each agent, characterized by demographic and psychographic attributes, receives policy signals and outputs multi-dimensional behavioral probability vectors. A calibration layer maps aggregated agent responses to observable population-level metrics, enabling validation against real-world data and deployment for counterfactual policy analysis. We instantiate this framework in the domain of pandemic response, using COVID-19 as a case study with rich observational data. On a held-out test period, our calibrated digital twin achieves a 20.7% improvement in macro-averaged prediction error over gradient boosting baselines across six behavioral categories. Counterfactual experiments demonstrate monotonic and bounded responses to policy variations, establishing behavioral plausibility. The framework is domain-agnostic: the same architecture applies to transportation policy, economic interventions, environmental regulations, or any setting where policy affects population behavior. We discuss implications for policy simulation, limitations of the approach, and directions for extending LLM-based digital twins beyond pandemic response.

---

### CBMAS: Cognitive Behavioral Modeling via Activation Steering

Authors: Ahmed H. Ismail, Anthony Kuang, Ayo Akinkugbe, Kevin Zhu, Sean O'Brien
Published: 2026-01-03
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2601.06109v1

Large language models (LLMs) often encode cognitive behaviors unpredictably across prompts, layers, and contexts, making them difficult to diagnose and control. We present CBMAS, a diagnostic framework for continuous activation steering, which extends cognitive bias analysis from discrete before/after interventions to interpretable trajectories. By combining steering vector construction with dense α-sweeps, logit lens-based bias curves, and layer-site sensitivity analysis, our approach can reveal tipping points where small intervention strengths flip model behavior and show how steering effects evolve across layer depth. We argue that these continuous diagnostics offer a bridge between high-level behavioral evaluation and low-level representational dynamics, contributing to the cognitive interpretability of LLMs. Lastly, we provide a CLI and datasets for various cognitive behaviors at the project repository, https://github.com/shimamooo/CBMAS.

---

### From RLHF to Direct Alignment: A Theoretical Unification of Preference Learning for Large Language Models

Authors: Tarun Raheja, Nilay Pochhi
Published: 2026-01-03
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2601.06108v1

Aligning large language models (LLMs) with human preferences has become essential for safe and beneficial AI deployment. While Reinforcement Learning from Human Feedback (RLHF) established the dominant paradigm, a proliferation of alternatives -- Direct Preference Optimization (DPO), Identity Preference Optimization (IPO), Kahneman-Tversky Optimization (KTO), Simple Preference Optimization (SimPO), and many others -- has left practitioners without clear guidance on method selection. This survey provides a \textit{theoretical unification} of preference learning methods, revealing that the apparent diversity reduces to principled choices along three orthogonal axes: \textbf{(I) Preference Model} (what likelihood model underlies the objective), \textbf{(II) Regularization Mechanism} (how deviation from reference policies is controlled), and \textbf{(III) Data Distribution} (online vs.\ offline learning and coverage requirements). We formalize each axis with precise definitions and theorems, establishing key results including the coverage separation between online and offline methods, scaling laws for reward overoptimization, and conditions under which direct alignment methods fail. Our analysis reveals that failure modes -- length hacking, mode collapse, likelihood displacement -- arise from specific, predictable combinations of design choices. We synthesize empirical findings across 50+ papers and provide a practitioner's decision guide for method selection. The framework transforms preference learning from an empirical art into a theoretically grounded discipline.

---

### Judge Model for Large-scale Multimodality Benchmarks

Authors: Min-Han Shih, Yu-Hsin Wu, Yu-Wei Chen
Published: 2026-01-03
Categories: cs.LG, cs.AI, cs.CL, cs.CV, cs.MA
arXiv: https://arxiv.org/abs/2601.06106v1

We propose a dedicated multimodal Judge Model designed to provide reliable, explainable evaluation across a diverse suite of tasks. Our benchmark spans text, audio, image, and video modalities, drawing from carefully sampled public datasets with fixed seeds to ensure reproducibility and minimize train test leakage. Instead of simple scoring, our framework aggregates multimodal judgments, analyzes the quality and reasoning consistency of model outputs, and generates diagnostic feedback. We evaluate several MLLMs, including Gemini 2.5, Phi 4, and Qwen 2.5, across 280 multimodal samples and compare judge model assessments with human annotators. Results show strong alignment between the Judge Model and human scores, demonstrating its potential as a scalable, interpretable evaluation pipeline for future multimodal AI research.

---

### Australian Bushfire Intelligence with AI-Driven Environmental Analytics

Authors: Tanvi Jois, Hussain Ahmad, Fatima Noor, Faheem Ullah
Published: 2026-01-03
Categories: cs.LG, cs.CY
arXiv: https://arxiv.org/abs/2601.06105v1

Bushfires are among the most destructive natural hazards in Australia, causing significant ecological, economic, and social damage. Accurate prediction of bushfire intensity is therefore essential for effective disaster preparedness and response. This study examines the predictive capability of spatio-temporal environmental data for identifying high-risk bushfire zones across Australia. We integrated historical fire events from NASA FIRMS, daily meteorological observations from Meteostat, and vegetation indices such as the Normalized Difference Vegetation Index (NDVI) from Google Earth Engine for the period 2015-2023. After harmonizing the datasets using spatial and temporal joins, we evaluated several machine learning models, including Random Forest, XGBoost, LightGBM, a Multi-Layer Perceptron (MLP), and an ensemble classifier. Under a binary classification framework distinguishing 'low' and 'high' fire risk, the ensemble approach achieved an accuracy of 87%. The results demonstrate that combining multi-source environmental features with advanced machine learning techniques can produce reliable bushfire intensity predictions, supporting more informed and timely disaster management.

---

### Comment on arXiv:2511.21731v1: Identifying Quantum Structure in AI Language: Evidence for Evolutionary Convergence of Human and Artificial Cognition

Authors: Krzysztof Sienicki
Published: 2026-01-03
Categories: cs.AI, cs.CL, quant-ph
arXiv: https://arxiv.org/abs/2601.06104v1

This note is a friendly technical check of arXiv:2511.21731v1. I highlight a few places where the manuscript's interpretation of (i) the reported CHSH/Bell-type calculations and (ii) Bose--Einstein (BE) fits to rank-frequency data seems to go beyond what the stated procedures can firmly support. I also point out one internal inconsistency in the "energy-level spacing" analogy. The aim is constructive: to keep the interesting empirical observations, while making clear what they do (and do not) imply about quantum entanglement in the usual Hilbert-space sense, especially when "energy" is defined by rank.

---

### The Impact of Post-training on Data Contamination

Authors: Muhammed Yusuf Kocyigit, Caglar Yildirim
Published: 2026-01-03
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.06103v1

We present a controlled study of how dataset contamination interacts with the post-training stages now standard in large language model training pipelines. Starting from clean checkpoints of Qwen2.5 (0.5B/1.5B) and Gemma3 (1B/4B), we inject five copies of GSM8K and MBPP test items into the first 2B tokens of an otherwise 25B token extended pre-training dataset. We then compare the contaminated and clean models both immediately after pre-training and again after two popular post-training methods: supervised fine-tuning (SFT) and reinforcement learning (RL) with group relative policy optimization (GRPO). The applied post-training steps do not have any contamination. Across math and coding benchmarks, we find three consistent patterns: (i) Contamination causes performance spikes that are gradually diminished with continued pre-training. After even 25B tokens the apparent performance inflation of contamination can become close to zero. (ii) Both SFT and GRPO resurface the leaked information, but with different external validity: SFT inflates scores only on the contaminated tasks, whereas GRPO also inflates performance on uncontaminated counterparts (GSMPlus, HumanEval). (iii) Model scale amplifies these tendencies, larger Supervised Fine Tuned models memorize more, while larger GRPO models translate leakage into more generalizable capabilities. Our results underscore the need for contamination audits \emph{after} post-training and suggest that RL-based post-training, although not immune, can help alleviate contamination-related over-estimation problems.

---

### Dynamic Intelligence Ceilings: Measuring Long-Horizon Limits of Planning and Creativity in Artificial Systems

Authors: Truong Xuan Khanh, Truong Quynh Hoa
Published: 2026-01-03
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2601.06102v1

Recent advances in artificial intelligence have produced systems capable of remarkable performance across a wide range of tasks. These gains, however, are increasingly accompanied by concerns regarding long-horizon developmental behavior, as many systems converge toward repetitive solution patterns rather than sustained growth. We argue that a central limitation of contemporary AI systems lies not in capability per se, but in the premature fixation of their performance frontier. To address this issue, we introduce the concept of a \emph{Dynamic Intelligence Ceiling} (DIC), defined as the highest level of effective intelligence attainable by a system at a given time under its current resources, internal intent, and structural configuration. To make this notion empirically tractable, we propose a trajectory-centric evaluation framework that measures intelligence as a moving frontier rather than a static snapshot. We operationalize DIC using two estimators: the \emph{Progressive Difficulty Ceiling} (PDC), which captures the maximal reliably solvable difficulty under constrained resources, and the \emph{Ceiling Drift Rate} (CDR), which quantifies the temporal evolution of this frontier. These estimators are instantiated through a procedurally generated benchmark that jointly evaluates long-horizon planning and structural creativity within a single controlled environment. Our results reveal a qualitative distinction between systems that deepen exploitation within a fixed solution manifold and those that sustain frontier expansion over time. Importantly, our framework does not posit unbounded intelligence, but reframes limits as dynamic and trajectory-dependent rather than static and prematurely fixed. \vspace{0.5em} \noindent\textbf{Keywords:} AI evaluation, planning and creativity, developmental intelligence, dynamic intelligence ceilings, complex adaptive systems

---

### How to Assess AI Literacy: Misalignment Between Self-Reported and Objective-Based Measures

Authors: Shan Zhang, Ruiwei Xiao, Anthony F. Botelho, Guanze Liao, Thomas K. F. Chiu, John Stamper, Kenneth R. Koedinger
Published: 2026-01-03
Categories: cs.CY, cs.AI
arXiv: https://arxiv.org/abs/2601.06101v1

The widespread adoption of Artificial Intelligence (AI) in K-12 education highlights the need for psychometrically-tested measures of teachers' AI literacy. Existing work has primarily relied on either self-report (SR) or objective-based (OB) assessments, with few studies aligning the two within a shared framework to compare perceived versus demonstrated competencies or examine how prior AI literacy experience shapes this relationship. This gap limits the scalability of learning analytics and the development of learner profile-driven instructional design. In this study, we developed and evaluated SR and OB measures of teacher AI literacy within the established framework of Concept, Use, Evaluate, and Ethics. Confirmatory factor analyses support construct validity with good reliability and acceptable fit. Results reveal a low correlation between SR and OB factors. Latent profile analysis identified six distinct profiles, including overestimation (SR > OB), underestimation (SR < OB), alignment (SR close to OB), and a unique low-SR/low-OB profile among teachers without AI literacy experience. Theoretically, this work extends existing AI literacy frameworks by validating SR and OB measures on shared dimensions. Practically, the instruments function as diagnostic tools for professional development, supporting AI-informed decisions (e.g., growth monitoring, needs profiling) and enabling scalable learning analytics interventions tailored to teacher subgroups.

---

### HyperCLOVA X 32B Think

Authors: NAVER Cloud HyperCLOVA X Team
Published: 2026-01-03
Categories: cs.CV, cs.AI, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2601.03286v1

In this report, we present HyperCLOVA X 32B Think, a vision-language model designed with particular emphasis on reasoning within the Korean linguistic and cultural context, as well as agentic ability. HyperCLOVA X 32B Think is pre-trained with a strong focus on reasoning capabilities and subsequently post-trained to support multimodal understanding, enhanced reasoning, agentic behaviors, and alignment with human preferences. Experimental evaluations against comparably sized models demonstrate that our model achieves strong performance on Korean text-to-text and vision-to-text benchmarks, as well as on agent-oriented evaluation tasks. By open-sourcing HyperCLOVA X 32B Think, we aim to support broader adoption and facilitate further research and innovation across both academic and industrial communities.

---

### Multimodal Sentiment Analysis based on Multi-channel and Symmetric Mutual Promotion Feature Fusion

Authors: Wangyuan Zhu, Jun Yu
Published: 2026-01-03
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2601.02415v1

Multimodal sentiment analysis is a key technology in the fields of human-computer interaction and affective computing. Accurately recognizing human emotional states is crucial for facilitating smooth communication between humans and machines. Despite some progress in multimodal sentiment analysis research, numerous challenges remain. The first challenge is the limited and insufficiently rich features extracted from single modality data. Secondly, most studies focus only on the consistency of inter-modal feature information, neglecting the differences between features, resulting in inadequate feature information fusion. In this paper, we first extract multi-channel features to obtain more comprehensive feature information. We employ dual-channel features in both the visual and auditory modalities to enhance intra-modal feature representation. Secondly, we propose a symmetric mutual promotion (SMP) inter-modal feature fusion method. This method combines symmetric cross-modal attention mechanisms and self-attention mechanisms, where the cross-modal attention mechanism captures useful information from other modalities, and the self-attention mechanism models contextual information. This approach promotes the exchange of useful information between modalities, thereby strengthening inter-modal interactions. Furthermore, we integrate intra-modal features and inter-modal fused features, fully leveraging the complementarity of inter-modal feature information while considering feature information differences. Experiments conducted on two benchmark datasets demonstrate the effectiveness and superiority of our proposed method.

---

### MIAR: Modality Interaction and Alignment Representation Fuison for Multimodal Emotion

Authors: Jichao Zhu, Jun Yu
Published: 2026-01-03
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2601.02414v1

Multimodal Emotion Recognition (MER) aims to perceive human emotions through three modes: language, vision, and audio. Previous methods primarily focused on modal fusion without adequately addressing significant distributional differences among modalities or considering their varying contributions to the task. They also lacked robust generalization capabilities across diverse textual model features, thus limiting performance in multimodal scenarios. Therefore, we propose a novel approach called Modality Interaction and Alignment Representation (MIAR). This network integrates contextual features across different modalities using a feature interaction to generate feature tokens to represent global representations of this modality extracting information from other modalities. These four tokens represent global representations of how each modality extracts information from others. MIAR aligns different modalities using contrastive learning and normalization strategies. We conduct experiments on two benchmarks: CMU-MOSI and CMU-MOSEI datasets, experimental results demonstrate the MIAR outperforms state-of-the-art MER methods.

---

### Accelerating Monte-Carlo Tree Search with Optimized Posterior Policies

Authors: Keith Frankston, Benjamin Howard
Published: 2026-01-03
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2601.01301v2

We introduce a recursive AlphaZero-style Monte--Carlo tree search algorithm, "RMCTS". The advantage of RMCTS over AlphaZero's MCTS-UCB is speed. In RMCTS, the search tree is explored in a breadth-first manner, so that network inferences naturally occur in large batches. This significantly reduces the GPU latency cost. We find that RMCTS is often more than 40 times faster than MCTS-UCB when searching a single root state, and about 3 times faster when searching a large batch of root states. The recursion in RMCTS is based on computing optimized posterior policies at each game state in the search tree, starting from the leaves and working back up to the root. Here we use the posterior policy explored in "Monte--Carlo tree search as regularized policy optimization" (Grill, et al.) Their posterior policy is the unique policy which maximizes the expected reward given estimated action rewards minus a penalty for diverging from the prior policy. The tree explored by RMCTS is not defined in an adaptive manner, as it is in MCTS-UCB. Instead, the RMCTS tree is defined by following prior network policies at each node. This is a disadvantage, but the speedup advantage is more significant, and in practice we find that RMCTS-trained networks match the quality of MCTS-UCB-trained networks in roughly one-third of the training time. We include timing and quality comparisons of RMCTS vs. MCTS-UCB for three games: Connect-4, Dots-and-Boxes, and Othello.

---

### T3C: Test-Time Tensor Compression with Consistency Guarantees

Authors: Ismail Lamaakal, Chaymae Yahyati, Yassine Maleh, Khalid El Makkaoui, Ibrahim Ouahbi
Published: 2026-01-03
Categories: cs.CL, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2601.01299v1

We present T3C, a train-once, test-time budget-conditioned compression framework that exposes rank and precision as a controllable deployment knob. T3C combines elastic tensor factorization (maintained up to a maximal rank) with rank-tied mixed-precision quantization and a lightweight controller that maps a latency/energy/size budget token to per-layer rank/bit assignments; the policy snaps to hardware-aligned profiles and is monotone in the budget. A fast, layerwise consistency certificate, computed from spectral proxies and activation statistics, upper-bounds logit drift and regularizes training, yielding a practical reliability signal with negligible overhead. On ImageNet-1k, T3C shifts the vision Pareto frontier: for ResNet-50 at matched accuracy (\leq 0.5% drop), p50 latency is 1.18ms with a 38MB model, outperforming PTQ-8b (1.44ms, 88MB); for ViT-B/16, T3C reaches 2.30ms p50 with 59MB, improving over strong PTQ/QAT baselines. A single T3C checkpoint therefore provides predictable, certificate-backed accuracy-latency-size trade-offs on demand across devices.

---

### Warp-Cortex: An Asynchronous, Memory-Efficient Architecture for Million-Agent Cognitive Scaling on Consumer Hardware

Authors: Jorge L. Ruiz Williams
Published: 2026-01-03
Categories: cs.LG, cs.AI, cs.AR, cs.DC, cs.MA
arXiv: https://arxiv.org/abs/2601.01298v1

Current multi-agent Large Language Model (LLM) frameworks suffer from linear memory scaling, rendering "System 2" parallel reasoning impractical on consumer hardware. We present Warp Cortex, an asynchronous architecture that theoretically enables million-agent cognitive scaling by decoupling agent logic from physical memory. Through Singleton Weight Sharing and a novel Topological Synapse--inspired by hybrid landmarking techniques from Topological Data Analysis (TDA)--we reduce memory complexity from O(N * L) to O(1) for weights and O(N * k) for context, where k << L. By treating the KV-cache as a point cloud in latent space, we apply witness-complex-inspired sparsification to preserve persistent homological features of the context manifold. On a single NVIDIA RTX 4090, we empirically demonstrate 100 concurrent agents at 2.2 GB total VRAM, with theoretical capacity exceeding 1,000 agents before compute latency becomes the bottleneck. We further introduce Referential Injection, a non-intrusive KV-cache update mechanism that allows asynchronous sub-agents to influence primary generation without stream disruption.

---

### ARGUS: Adaptive Rotation-Invariant Geometric Unsupervised System

Authors: Anantha Sharma
Published: 2026-01-03
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2601.01297v2

Detecting distributional drift in high-dimensional data streams presents fundamental challenges: global comparison methods scale poorly, projection-based approaches lose geometric structure, and re-clustering methods suffer from identity instability. This paper introduces Argus, A framework that reconceptualizes drift detection as tracking local statistics over a fixed spatial partition of the data manifold. The key contributions are fourfold. First, it is proved that Voronoi tessellations over canonical orthonormal frames yield drift metrics that are invariant to orthogonal transformations. The rotations and reflections that preserve Euclidean geometry. Second, it is established that this framework achieves O(N) complexity per snapshot while providing cell-level spatial localization of distributional change. Third, a graph-theoretic characterization of drift propagation is developed that distinguishes coherent distributional shifts from isolated perturbations. Fourth, product quantization tessellation is introduced for scaling to very high dimensions (d>500) by decomposing the space into independent subspaces and aggregating drift signals across subspaces. This paper formalizes the theoretical foundations, proves invariance properties, and presents experimental validation demonstrating that the framework correctly identifies drift under coordinate rotation while existing methods produce false positives. The tessellated approach offers a principled geometric foundation for distribution monitoring that preserves high-dimensional structure without the computational burden of pairwise comparisons.

---

### Aggressive Compression Enables LLM Weight Theft

Authors: Davis Brown, Juan-Pablo Rivera, Dan Hendrycks, Mantas Mazeika
Published: 2026-01-03
Categories: cs.CR, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2601.01296v1

As frontier AIs become more powerful and costly to develop, adversaries have increasing incentives to steal model weights by mounting exfiltration attacks. In this work, we consider exfiltration attacks where an adversary attempts to sneak model weights out of a datacenter over a network. While exfiltration attacks are multi-step cyber attacks, we demonstrate that a single factor, the compressibility of model weights, significantly heightens exfiltration risk for large language models (LLMs). We tailor compression specifically for exfiltration by relaxing decompression constraints and demonstrate that attackers could achieve 16x to 100x compression with minimal trade-offs, reducing the time it would take for an attacker to illicitly transmit model weights from the defender's server from months to days. Finally, we study defenses designed to reduce exfiltration risk in three distinct ways: making models harder to compress, making them harder to 'find,' and tracking provenance for post-attack analysis using forensic watermarks. While all defenses are promising, the forensic watermark defense is both effective and cheap, and therefore is a particularly attractive lever for mitigating weight-exfiltration risk.

---

### Sobolev Approximation of Deep ReLU Networks in Log-Barron Space

Authors: Changhoon Song, Seungchan Ko, Youngjoon Hong
Published: 2026-01-03
Categories: cs.LG, math.NA
arXiv: https://arxiv.org/abs/2601.01295v2

Universal approximation theorems show that neural networks can approximate any continuous function; however, the number of parameters may grow exponentially with the ambient dimension, so these results do not fully explain the practical success of deep models on high-dimensional data. Barron space theory addresses this: if a target function belongs to a Barron space, a two-layer network with $n$ parameters achieves an $O(n^{-1/2})$ approximation error in $L^2$. Yet classical Barron spaces $\mathscr{B}^{s+1}$ still require stronger regularity than Sobolev spaces $H^s$, and existing depth-sensitive results often assume constraints such as $sL \le 1/2$. In this paper, we introduce a log-weighted Barron space $\mathscr{B}^{\log}$, which requires a strictly weaker assumption than $\mathscr{B}^s$ for any $s>0$. For this new function space, we first study embedding properties and carry out a statistical analysis via the Rademacher complexity. Then we prove that functions in $\mathscr{B}^{\log}$ can be approximated by deep ReLU networks with explicit depth dependence. We then define a family $\mathscr{B}^{s,\log}$, establish approximation bounds in the $H^1$ norm, and identify maximal depth scales under which these rates are preserved. Our results clarify how depth reduces regularity requirements for efficient representation, offering a more precise explanation for the performance of deep architectures beyond the classical Barron setting, and for their stable use in high-dimensional problems used today.

---

### Diffusion Timbre Transfer Via Mutual Information Guided Inpainting

Authors: Ching Ho Lee, Javier Nistal, Stefan Lattner, Marco Pasini, George Fazekas
Published: 2026-01-03
Categories: cs.SD, cs.AI, eess.AS
arXiv: https://arxiv.org/abs/2601.01294v2

We study timbre transfer as an inference-time editing problem for music audio. Starting from a strong pre-trained latent diffusion model, we introduce a lightweight procedure that requires no additional training: (i) a dimension-wise noise injection that targets latent channels most informative of instrument identity, and (ii) an early-step clamping mechanism that re-imposes the input's melodic and rhythmic structure during reverse diffusion. The method operates directly on audio latents and is compatible with text/audio conditioning (e.g., CLAP). We discuss design choices,analyze trade-offs between timbral change and structural preservation, and show that simple inference-time controls can meaningfully steer pre-trained models for style-transfer use cases.

---

### The Alchemy of Thought: Understanding In-Context Learning Through Supervised Classification

Authors: Harshita Narnoli, Mihai Surdeanu
Published: 2026-01-03
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.01290v1

In-context learning (ICL) has become a prominent paradigm to rapidly customize LLMs to new tasks without fine-tuning. However, despite the empirical evidence of its usefulness, we still do not truly understand how ICL works. In this paper, we compare the behavior of in-context learning with supervised classifiers trained on ICL demonstrations to investigate three research questions: (1) Do LLMs with ICL behave similarly to classifiers trained on the same examples? (2) If so, which classifiers are closer, those based on gradient descent (GD) or those based on k-nearest neighbors (kNN)? (3) When they do not behave similarly, what conditions are associated with differences in behavior? Using text classification as a use case, with six datasets and three LLMs, we observe that LLMs behave similarly to these classifiers when the relevance of demonstrations is high. On average, ICL is closer to kNN than logistic regression, giving empirical evidence that the attention mechanism behaves more similarly to kNN than GD. However, when demonstration relevance is low, LLMs perform better than these classifiers, likely because LLMs can back off to their parametric memory, a luxury these classifiers do not have.

---

### PyBatchRender: A Python Library for Batched 3D Rendering at Up to One Million FPS

Authors: Evgenii Rudakov, Jonathan Shock, Benjamin Ultan Cowley
Published: 2026-01-03
Categories: cs.GR, cs.AI, cs.PF, cs.RO
arXiv: https://arxiv.org/abs/2601.01288v1

Reinforcement learning from pixels is often bottlenecked by the performance and complexity of 3D rendered environments. Researchers face a trade-off between high-speed, low-level engines and slower, more accessible Python frameworks. To address this, we introduce PyBatchRender, a Python library for high-throughput, batched 3D rendering that achieves over 1 million FPS on simple scenes. Built on the Panda3D game engine, it utilizes its mature ecosystem while enhancing performance through optimized batched rendering for up to 1000X speedups. Designed as a physics-agnostic renderer for reinforcement learning from pixels, PyBatchRender offers greater flexibility than dedicated libraries, simpler setup than typical game-engine wrappers, and speeds rivaling state-of-the-art C++ engines like Madrona. Users can create custom scenes entirely in Python with tens of lines of code, enabling rapid prototyping for scalable AI training. Open-source and easy to integrate, it serves to democratize high-performance 3D simulation for researchers and developers. The library is available at https://github.com/dolphin-in-a-coma/PyBatchRender.

---

### S2M-Net: Spectral-Spatial Mixing for Medical Image Segmentation with Morphology-Aware Adaptive Loss

Authors: Md. Sanaullah Chowdhury Lameya Sabrin
Published: 2026-01-03
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.01285v2

Medical image segmentation requires balancing local precision for boundary-critical clinical applications, global context for anatomical coherence, and computational efficiency for deployment on limited data and hardware a trilemma that existing architectures fail to resolve. Although convolutional networks provide local precision at $\mathcal{O}(n)$ cost but limited receptive fields, vision transformers achieve global context through $\mathcal{O}(n^2)$ self-attention at prohibitive computational expense, causing overfitting on small clinical datasets. We propose S2M-Net, a 4.7M-parameter architecture that achieves $\mathcal{O}(HW \log HW)$ global context through two synergistic innovations: (i) Spectral-Selective Token Mixer (SSTM), which exploits the spectral concentration of medical images via truncated 2D FFT with learnable frequency filtering and content-gated spatial projection, avoiding quadratic attention cost while maintaining global receptive fields; and (ii) Morphology-Aware Adaptive Segmentation Loss (MASL), which automatically analyzes structure characteristics (compactness, tubularity, irregularity, scale) to modulate five complementary loss components through constrained learnable weights, eliminating manual per-dataset tuning. Comprehensive evaluation in 16 medical imaging datasets that span 8 modalities demonstrates state-of-the-art performance: 96.12\% Dice on polyp segmentation, 83.77\% on surgical instruments (+17.85\% over the prior art) and 80.90\% on brain tumors, with consistent 3-18\% improvements over specialized baselines while using 3.5--6$\times$ fewer parameters than transformer-based methods.

---

### AI-Powered Deepfake Detection Using CNN and Vision Transformer Architectures

Authors: Sifatullah Sheikh Urmi, Kirtonia Nuzath Tabassum Arthi, Md Al-Imran
Published: 2026-01-03
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2601.01281v1

The increasing use of artificial intelligence generated deepfakes creates major challenges in maintaining digital authenticity. Four AI-based models, consisting of three CNNs and one Vision Transformer, were evaluated using large face image datasets. Data preprocessing and augmentation techniques improved model performance across different scenarios. VFDNET demonstrated superior accuracy with MobileNetV3, showing efficient performance, thereby demonstrating AI's capabilities for dependable deepfake detection.

---

### Does Memory Need Graphs? A Unified Framework and Empirical Analysis for Long-Term Dialog Memory

Authors: Sen Hu, Yuxiang Wei, Jiaxin Ran, Zhiyuan Yao, Xueran Han, Huacan Wang, Ronghao Chen, Lei Zou
Published: 2026-01-03
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2601.01280v3

Graph structures are increasingly used in dialog memory systems, but empirical findings on their effectiveness remain inconsistent, making it unclear which design choices truly matter. We present an experimental, system-oriented analysis of long-term dialog memory architectures. We introduce a unified framework that decomposes dialog memory systems into core components and supports both graph-based and non-graph approaches. Under this framework, we conduct controlled, stage-wise experiments on LongMemEval and HaluMem, comparing common design choices in memory representation, organization, maintenance, and retrieval. Our results show that many performance differences are driven by foundational system settings rather than specific architectural innovations. Based on these findings, we identify stable and reliable strong baselines for future dialog memory research. Code are available at https://github.com/AvatarMemory/UnifiedMem

---

### Supracompetitive Pricing Under AI Monoculture

Authors: Shengyu Cao, Ming Hu
Published: 2026-01-03
Categories: econ.TH, cs.AI, cs.CE, cs.CL, cs.GT
arXiv: https://arxiv.org/abs/2601.01279v3

When competing sellers delegate pricing to a shared AI model, such as a large language model, correlated recommendations combined with performance-driven updates aggregating seller feedback raise a key question: can standard AI deployment practices inadvertently produce supracompetitive pricing? We develop a stylized duopoly model in which two sellers receive pricing recommendations from a shared AI characterized by two parameters: a propensity parameter capturing the model's tendency to set high prices and an output-fidelity parameter measuring alignment between this tendency and actual outputs, with propensity updated via periodic retraining on observed outcomes. We find that configuring AI models for robustness and reproducibility can lead to supracompetitive pricing via a phase transition. Below a critical output-fidelity threshold, competitive pricing is the unique stable outcome. Above it, the model exhibits bistability: both competitive and supracompetitive pricing are locally stable, with the realized outcome determined by the model's initial propensity. Supracompetitive pricing raises average prices, but occasional low-price recommendations complicate detection. With perfect output fidelity, full price coordination emerges from any interior initial propensity. For finite training batches of size $b$, when the initial propensity lies in the supracompetitive basin, the probability of supracompetitive pricing approaches 1 as $b$ increases, with the region of indeterminate outcomes shrinking at rate $O(1/\sqrt{b})$. Any factor reducing alignment between the model's propensity and sellers' actual pricing, whether through diversifying AI providers, introducing recommendation noise, or reducing seller adherence, pushes the market toward competitive outcomes.

---

### An Energy-Efficient Smart Bus Transport Management System with Blind-Spot Collision Detection Ability

Authors: Md. Sadman Haque, Zobaer Ibn Razzaque, Robiul Awoul Robin, Fahim Hafiz, Riasat Azim
Published: 2026-01-03
Categories: eess.SY, cs.CV
arXiv: https://arxiv.org/abs/2601.01274v1

Public bus transport systems in developing countries often suffer from a lack of real-time location updates and for users, making commuting inconvenient and unreliable for passengers. Furthermore, stopping at undesired locations rather than designated bus stops creates safety risks and contributes to roadblocks, often causing traffic congestion. Additionally, issues such as blind spots, along with a lack of following traffic laws, increase the chances of accidents. In this work, we address these challenges by proposing a smart public bus system along with intelligent bus stops that enhance safety, efficiency, and sustainability. Our approach includes a deep learning-based blind-spot warning system to help drivers avoid accidents with automated bus-stop detection to accurately identify bus stops, improving transit efficiency. We also introduce IoT-based solar-powered smart bus stops that show real-time passenger counts, along with an RFID-based card system to track where passengers board and exit. A smart door system ensures safer and more organised boarding, while real-time bus tracking keeps passengers informed. To connect all these features, we use an HTTP-based server for seamless communication between the interconnected network systems. Our proposed system demonstrated approximately 99% efficiency in real-time blind spot detection while stopping precisely at the bus stops. Furthermore, the server showed real-time location updates both to the users and at the bus stops, enhancing commuting efficiency. The proposed energy-efficient bus stop demonstrated 12.71kWh energy saving, promoting sustainable architecture. Full implementation and source code are available at: https://github.com/sadman-adib/MoveMe-IoT

---

### Accelerated Full Waveform Inversion by Deep Compressed Learning

Authors: Maayan Gelboim, Amir Adler, Mauricio Araya-Polo
Published: 2026-01-03
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.01268v1

We propose and test a method to reduce the dimensionality of Full Waveform Inversion (FWI) inputs as computational cost mitigation approach. Given modern seismic acquisition systems, the data (as input for FWI) required for an industrial-strength case is in the teraflop level of storage, therefore solving complex subsurface cases or exploring multiple scenarios with FWI become prohibitive. The proposed method utilizes a deep neural network with a binarized sensing layer that learns by compressed learning a succinct but consequential seismic acquisition layout from a large corpus of subsurface models. Thus, given a large seismic data set to invert, the trained network selects a smaller subset of the data, then by using representation learning, an autoencoder computes latent representations of the data, followed by K-means clustering of the latent representations to further select the most relevant data for FWI. Effectively, this approach can be seen as a hierarchical selection. The proposed approach consistently outperforms random data sampling, even when utilizing only 10% of the data for 2D FWI, these results pave the way to accelerating FWI in large scale 3D inversion.

---

### From Policy to Logic for Efficient and Interpretable Coverage Assessment

Authors: Rhitabrat Pokharel, Hamid Reza Hassanzadeh, Ameeta Agrawal
Published: 2026-01-03
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2601.01266v2

Large Language Models (LLMs) have demonstrated strong capabilities in interpreting lengthy, complex legal and policy language. However, their reliability can be undermined by hallucinations and inconsistencies, particularly when analyzing subjective and nuanced documents. These challenges are especially critical in medical coverage policy review, where human experts must be able to rely on accurate information. In this paper, we present an approach designed to support human reviewers by making policy interpretation more efficient and interpretable. We introduce a methodology that pairs a coverage-aware retriever with symbolic rule-based reasoning to surface relevant policy language, organize it into explicit facts and rules, and generate auditable rationales. This hybrid system minimizes the number of LLM inferences required which reduces overall model cost. Notably, our approach achieves a 44% reduction in inference cost alongside a 4.5% improvement in F1 score, demonstrating both efficiency and effectiveness.

---

### MambaFormer: Token-Level Guided Routing Mixture-of-Experts for Accurate and Efficient Clinical Assistance

Authors: Hamad Khan, Saddam Hussain Khan
Published: 2026-01-03
Categories: cs.CV, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2601.01260v1

The deployment of large language models (LLMs) in real-world clinical applications is constrained by the fundamental trade-off between computational cost and the efficiency of linear-time models. To address this, we propose an LLM-based MambaFormer hybrid Mixture-of-Experts (MoE) framework for efficient medical question-answering (QA) and clinical assistance. The MambaFormer employs a lightweight gating mechanism that performs token-level dynamic routing to a customized Transformer expert (ET5) for short, complex queries or to a State Space Model expert (EMamba) for long, high-throughput sequences. The customized EMamba and ET5 models are tailored to accommodate input sequence dimensionality, embedding structure, sequence length, and target-specific output heads, and are fine-tuned through transfer learning on a new, custom-designed DentalQA dataset. Moreover, intelligent routing decisions are driven by the contextual complexity of token embeddings, normalized sequence length, and domain-aware features, thereby enforcing a Pareto-optimal trade-off between inference latency and prediction accuracy. Furthermore, a novel utility-guided multi-objective loss jointly optimizes decisions, router parameters, routing behavior, expert utilization, and computational cost by adaptively regulating token-level expert activation. Finally, the proposed MambaFormer is cross-validated (holdout) for medical QA on the new, custom-designed DentalQA and PubMedQA datasets and compared with state-of-the-art techniques. The proposed MambaFormer outperforms (BERTScore = 0.9180) with ultra-low latency (0.077 s), delivering a 24.4 speedup over T5-Large and establishing a scalable solution for resource-constrained clinical deployment.

---

### Seamlessly Natural: Image Stitching with Natural Appearance Preservation

Authors: Gaetane Lorna N. Tchana, Damaris Belle M. Fotso, Antonio Hendricks, Christophe Bobda
Published: 2026-01-03
Categories: eess.IV, cs.AI, cs.CV, cs.GR, eess.SP
arXiv: https://arxiv.org/abs/2601.01257v1

This paper introduces SENA (SEamlessly NAtural), a geometry-driven image stitching approach that prioritizes structural fidelity in challenging real-world scenes characterized by parallax and depth variation. Conventional image stitching relies on homographic alignment, but this rigid planar assumption often fails in dual-camera setups with significant scene depth, leading to distortions such as visible warps and spherical bulging. SENA addresses these fundamental limitations through three key contributions. First, we propose a hierarchical affine-based warping strategy, combining global affine initialization with local affine refinement and smooth free-form deformation. This design preserves local shape, parallelism, and aspect ratios, thereby avoiding the hallucinated structural distortions commonly introduced by homography-based models. Second, we introduce a geometry-driven adequate zone detection mechanism that identifies parallax-minimized regions directly from the disparity consistency of RANSAC-filtered feature correspondences, without relying on semantic segmentation. Third, building upon this adequate zone, we perform anchor-based seamline cutting and segmentation, enforcing a one-to-one geometric correspondence across image pairs by construction, which effectively eliminates ghosting, duplication, and smearing artifacts in the final panorama. Extensive experiments conducted on challenging datasets demonstrate that SENA achieves alignment accuracy comparable to leading homography-based methods, while significantly outperforming them in critical visual metrics such as shape preservation, texture integrity, and overall visual realism.

---

### Entity-Aware and Secure Query Optimization in Database Using Named Entity Recognition

Authors: Azrin Sultana, Hasibur Rashid Chayon
Published: 2026-01-03
Categories: cs.DB, cs.CL
arXiv: https://arxiv.org/abs/2601.01254v1

Cloud storage has become the backbone of modern data infrastructure, yet privacy and efficient data retrieval remain significant challenges. Traditional privacy-preserving approaches primarily focus on enhancing database security but fail to address the automatic identification of sensitive information before encryption. This can dramatically reduce query processing time and mitigate errors during manual identification of sensitive information, thereby reducing potential privacy risks. To address this limitation, this research proposes an intelligent privacy-preserving query optimization framework that integrates Named Entity Recognition (NER) to detect sensitive information in queries, utilizing secure data encryption and query optimization techniques for both sensitive and non-sensitive data in parallel, thereby enabling efficient database optimization. Combined deep learning algorithms and transformer-based models to detect and classify sensitive entities with high precision, and the Advanced Encryption Standard (AES) algorithm to encrypt, with blind indexing to secure search functionality of the sensitive data, whereas non-sensitive data was divided into groups using the K-means algorithm, along with a rank search for optimization. Among all NER models, the Deep Belief Network combined with Long Short-Term Memory (DBN-LSTM) delivers the best performance, with an accuracy of 93% and precision (94%), recall, and F1 score of 93%, and 93%, respectively. Besides, encrypted search achieved considerably faster results with the help of blind indexing, and non-sensitive data fetching also outperformed traditional clustering-based searches. By integrating sensitive data detection, encryption, and query optimization, this work advances the state of privacy-preserving computation in modern cloud infrastructures.

---

### Stochastic Control Methods for Optimization

Authors: Jinniao Qiu
Published: 2026-01-03
Categories: math.OC, cs.LG, math.NA, math.PR
arXiv: https://arxiv.org/abs/2601.01248v4

In this work, we investigate a stochastic control framework for global optimization over both Euclidean spaces and the Wasserstein space of probability measures, where the objective function may be non-convex and/or non-differentiable. In the Euclidean setting, the original minimization problem is approximated by a family of regularized stochastic control problems; using dynamic programming, we analyze the associated Hamilton-Jacobi-Bellman equations and obtain tractable representations via the Cole-Hopf transformation and the Feynman-Kac formula. For optimization over probability measures, we formulate a regularized mean-field control problem characterized by a master equation, and further approximate it by controlled $N$-particle systems. We establish that, as the regularization parameter tends to zero (and as the particle number tends to infinity for the optimization over probability measures), the value of the control problem converges to the global minimum of the original objective. Building on the resulting probabilistic representations, we propose the Monte Carlo-based numerical schemes that are derivative-free due to the utilization of the Bismut-Elworthy-Li formula and numerical experiments are reported to illustrate the effectiveness of the methods and to support the theoretical convergence rates.

---

### Racka: Efficient Hungarian LLM Adaptation on Academic Infrastructure

Authors: Zsolt Csibi, Bence György Gortka, Natabara Gyöngyössy, Kornél Nagy, Dávid Márk Nemeskey, Martin Sallai, András Simonyi, András Márk Szekeres, Gábor Palkó
Published: 2026-01-03
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.01244v2

We present Racka, a lightweight, continually pretrained large language model designed to bridge the resource gap between Hungarian and high-resource languages such as English and German. Racka employs parameter-efficient continual pretraining via Low-Rank Adaptation (LoRA) on a Qwen-3 4B backbone, making the recipe practical on A100 (40GB)-based HPC clusters with low inter-node bandwidth. To better match the training distribution, we replace and adapt the tokenizer, achieving substantially improved tokenization fertility for Hungarian while maintaining competitive performance in English and German. The model is trained on 160B subword tokens drawn from a mixture of internet and high-quality curated sources, with a composition of 44% Hungarian, 24% English, 21% German, and 11% code. This data mix is chosen to mitigate catastrophic forgetting and preserve high-resource language capabilities during continual pretraining. Our preliminary results indicate modest but stable results in language adaptation.

---

### RFAssigner: A Generic Label Assignment Strategy for Dense Object Detection

Authors: Ziqian Guan, Xieyi Fu, Yuting Wang, Haowen Xiao, Jiarui Zhu, Yingying Zhu, Yongtao Liu, Lin Gu
Published: 2026-01-03
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.01240v1

Label assignment is a critical component in training dense object detectors. State-of-the-art methods typically assign each training sample a positive and a negative weight, optimizing the assignment scheme during training. However, these strategies often assign an insufficient number of positive samples to small objects, leading to a scale imbalance during training. To address this limitation, we introduce RFAssigner, a novel assignment strategy designed to enhance the multi-scale learning capabilities of dense detectors. RFAssigner first establishes an initial set of positive samples using a point-based prior. It then leverages a Gaussian Receptive Field (GRF) distance to measure the similarity between the GRFs of unassigned candidate locations and the ground-truth objects. Based on this metric, RFAssigner adaptively selects supplementary positive samples from the unassigned pool, promoting a more balanced learning process across object scales. Comprehensive experiments on three datasets with distinct object scale distributions validate the effectiveness and generalizability of our method. Notably, a single FCOS-ResNet-50 detector equipped with RFAssigner achieves state-of-the-art performance across all object scales, consistently outperforming existing strategies without requiring auxiliary modules or heuristics.

---

### Evidence Slopes and Effective Dimension in Singular Linear Models

Authors: Kalyaan Rao
Published: 2026-01-03
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2601.01238v1

Bayesian model selection commonly relies on Laplace approximation or the Bayesian Information Criterion (BIC), which assume that the effective model dimension equals the number of parameters. Singular learning theory replaces this assumption with the real log canonical threshold (RLCT), an effective dimension that can be strictly smaller in overparameterized or rank-deficient models. We study linear-Gaussian rank models and linear subspace (dictionary) models in which the exact marginal likelihood is available in closed form and the RLCT is analytically tractable. In this setting, we show theoretically and empirically that the error of Laplace/BIC grows linearly with (d/2 minus lambda) times log n, where d is the ambient parameter dimension and lambda is the RLCT. An RLCT-aware correction recovers the correct evidence slope and is invariant to overcomplete reparameterizations that represent the same data subspace. Our results provide a concrete finite-sample characterization of Laplace failure in singular models and demonstrate that evidence slopes can be used as a practical estimator of effective dimension in simple linear settings.

---

### Benchmarking the Computational and Representational Efficiency of State Space Models against Transformers on Long-Context Dyadic Sessions

Authors: Abidemi Koledoye, Chinemerem Unachukwu, Gold Nwobu, Hasin Rana
Published: 2026-01-03
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.01237v1

State Space Models (SSMs) have emerged as a promising alternative to Transformers for long-context sequence modeling, offering linear $O(N)$ computational complexity compared to the Transformer's quadratic $O(N^2)$ scaling. This paper presents a comprehensive benchmarking study comparing the Mamba SSM against the LLaMA Transformer on long-context sequences, using dyadic therapy sessions as a representative test case. We evaluate both architectures across two dimensions: (1) computational efficiency, where we measure memory usage and inference speed from 512 to 8,192 tokens, and (2) representational efficiency, where we analyze hidden state dynamics and attention patterns. Our findings provide actionable insights for practitioners working with long-context applications, establishing precise conditions under which SSMs offer advantages over Transformers.

---

### The Dependency Divide: An Interpretable Machine Learning Framework for Profiling Student Digital Satisfaction in the Bangladesh Context

Authors: Md Muhtasim Munif Fahim, Humyra Ankona, Md Monimul Huq, Md Rezaul Karim
Published: 2026-01-03
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.01231v1

Background: While digital access has expanded rapidly in resource-constrained contexts, satisfaction with digital learning platforms varies significantly among students with seemingly equal connectivity. Traditional digital divide frameworks fail to explain these variations. Purpose: This study introduces the "Dependency Divide", a novel framework proposing that highly engaged students become conditionally vulnerable to infrastructure failures, challenging assumptions that engagement uniformly benefits learners in post-access environments. Methods: We conducted a cross-sectional study of 396 university students in Bangladesh using a three-stage analytical approach: (1) stability-validated K-prototypes clustering to identify student profiles, (2) profile-specific Random Forest models with SHAP and ALE analysis to determine satisfaction drivers, and (3) formal interaction analysis with propensity score matching to test the Dependency Divide hypothesis. Results: Three distinct profiles emerged: Casually Engaged (58%), Efficient Learners (35%), and Hyper-Engaged (7%). A significant interaction between educational device time and internet reliability (\b{eta} = 0.033, p = 0.028) confirmed the Dependency Divide: engagement increased satisfaction only when infrastructure remained reliable. Hyper-Engaged students showed greatest vulnerability despite or because of their sophisticated digital workflows. Policy simulations demonstrated that targeted reliability improvements for high-dependency users yielded 2.06 times greater returns than uniform interventions. Conclusions: In fragile infrastructure contexts, capability can become liability. Digital transformation policies must prioritize reliability for dependency-prone users, establish contingency systems, and educate students about dependency risks rather than uniformly promoting engagement.

---

### NeuroSSM: Multiscale Differential State-Space Modeling for Context-Aware fMRI Analysis

Authors: Furkan Genç, Boran İsmet Macun, Sait Sarper Özaslan, Emine U. Saritas, Tolga Çukur
Published: 2026-01-03
Categories: eess.SP, cs.LG
arXiv: https://arxiv.org/abs/2601.01229v1

Accurate fMRI analysis requires sensitivity to temporal structure across multiple scales, as BOLD signals encode cognitive processes that emerge from fast transient dynamics to slower, large-scale fluctuations. Existing deep learning (DL) approaches to temporal modeling face challenges in jointly capturing these dynamics over long fMRI time series. Among current DL models, transformers address long-range dependencies by explicitly modeling pairwise interactions through attention, but the associated quadratic computational cost limits effective integration of temporal dependencies across long fMRI sequences. Selective state-space models (SSMs) instead model long-range temporal dependencies implicitly through latent state evolution in a dynamical system, enabling efficient propagation of dependencies over time. However, recent SSM-based approaches for fMRI commonly operate on derived functional connectivity representations and employ single-scale temporal processing. These design choices constrain the ability to jointly represent fast transient dynamics and slower global trends within a single model. We propose NeuroSSM, a selective state-space architecture designed for end-to-end analysis of raw BOLD signals in fMRI time series. NeuroSSM addresses the above limitations through two complementary design components: a multiscale state-space backbone that captures fast and slow dynamics concurrently, and a parallel differencing branch that increases sensitivity to transient state changes. Experiments on clinical and non-clinical datasets demonstrate that NeuroSSM achieves competitive performance and efficiency against state-of-the-art fMRI analysis methods.

---

### HyDRA: Hybrid Denoising Regularization for Measurement-Only DEQ Training

Authors: Markus Haltmeier, Lukas Neumann, Nadja Gruber, Johannes Schwab, Gyeongha Hwang
Published: 2026-01-03
Categories: cs.CV, math.NA
arXiv: https://arxiv.org/abs/2601.01228v1

Solving image reconstruction problems of the form \(\mathbf{A} \mathbf{x} = \mathbf{y}\) remains challenging due to ill-posedness and the lack of large-scale supervised datasets. Deep Equilibrium (DEQ) models have been used successfully but typically require supervised pairs \((\mathbf{x},\mathbf{y})\). In many practical settings, only measurements \(\mathbf{y}\) are available. We introduce HyDRA (Hybrid Denoising Regularization Adaptation), a measurement-only framework for DEQ training that combines measurement consistency with an adaptive denoising regularization term, together with a data-driven early stopping criterion. Experiments on sparse-view CT demonstrate competitive reconstruction quality and fast inference.

---

### Stylometry Analysis of Human and Machine Text for Academic Integrity

Authors: Hezam Albaqami, Muhammad Asif Ayub, Nasir Ahmad, Yaseen Ahmad, Mohammed M. Alqahtani, Abdullah M. Algamdi, Almoaid A. Owaidah, Kashif Ahmad
Published: 2026-01-03
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2601.01225v1

This work addresses critical challenges to academic integrity, including plagiarism, fabrication, and verification of authorship of educational content, by proposing a Natural Language Processing (NLP)-based framework for authenticating students' content through author attribution and style change detection. Despite some initial efforts, several aspects of the topic are yet to be explored. In contrast to existing solutions, the paper provides a comprehensive analysis of the topic by targeting four relevant tasks, including (i) classification of human and machine text, (ii) differentiating in single and multi-authored documents, (iii) author change detection within multi-authored documents, and (iv) author recognition in collaboratively produced documents. The solutions proposed for the tasks are evaluated on two datasets generated with Gemini using two different prompts, including a normal and a strict set of instructions. During experiments, some reduction in the performance of the proposed solutions is observed on the dataset generated through the strict prompt, demonstrating the complexities involved in detecting machine-generated text with cleverly crafted prompts. The generated datasets, code, and other relevant materials are made publicly available on GitHub, which are expected to provide a baseline for future research in the domain.

---

### Improved Object-Centric Diffusion Learning with Registers and Contrastive Alignment

Authors: Bac Nguyen, Yuhta Takida, Naoki Murata, Chieh-Hsin Lai, Toshimitsu Uesaka, Stefano Ermon, Yuki Mitsufuji
Published: 2026-01-03
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2601.01224v2

Slot Attention (SA) with pretrained diffusion models has recently shown promise for object-centric learning (OCL), but suffers from slot entanglement and weak alignment between object slots and image content. We propose Contrastive Object-centric Diffusion Alignment (CODA), a simple extension that (i) employs register slots to absorb residual attention and reduce interference between object slots, and (ii) applies a contrastive alignment loss to explicitly encourage slot-image correspondence. The resulting training objective serves as a tractable surrogate for maximizing mutual information (MI) between slots and inputs, strengthening slot representation quality. On both synthetic (MOVi-C/E) and real-world datasets (VOC, COCO), CODA improves object discovery (e.g., +6.1% FG-ARI on COCO), property prediction, and compositional image generation over strong baselines. Register slots add negligible overhead, keeping CODA efficient and scalable. These results indicate potential applications of CODA as an effective framework for robust OCL in complex, real-world scenes. Code and pretrained models are available at https://github.com/sony/coda.

---

### Adaptive Conformal Prediction via Bayesian Uncertainty Weighting for Hierarchical Healthcare Data

Authors: Marzieh Amiri Shahbazi, Ali Baheri, Nasibeh Azadeh-Fard
Published: 2026-01-03
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2601.01223v1

Clinical decision-making demands uncertainty quantification that provides both distribution-free coverage guarantees and risk-adaptive precision, requirements that existing methods fail to jointly satisfy. We present a hybrid Bayesian-conformal framework that addresses this fundamental limitation in healthcare predictions. Our approach integrates Bayesian hierarchical random forests with group-aware conformal calibration, using posterior uncertainties to weight conformity scores while maintaining rigorous coverage validity. Evaluated on 61,538 admissions across 3,793 U.S. hospitals and 4 regions, our method achieves target coverage (94.3% vs 95% target) with adaptive precision: 21% narrower intervals for low-uncertainty cases while appropriately widening for high-risk predictions. Critically, we demonstrate that well-calibrated Bayesian uncertainties alone severely under-cover (14.1%), highlighting the necessity of our hybrid approach. This framework enables risk-stratified clinical protocols, efficient resource planning for high-confidence predictions, and conservative allocation with enhanced oversight for uncertain cases, providing uncertainty-aware decision support across diverse healthcare settings.

---