# Research Papers — 2026-01 · bundle page 111 of 189 > Full-text markdown of papers #5501–5550 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/111 [← Previous bundle](https://aipod.dev/papers/archive/2026-01/page/110.md) [Next bundle →](https://aipod.dev/papers/archive/2026-01/page/112.md) ### Kinematic Tokenization: Optimization-Based Continuous-Time Tokens for Learnable Decision Policies in Noisy Time Series Authors: Griffin Kearney Published: 2026-01-15 Categories: cs.LG, cs.AI, math.OC arXiv: https://arxiv.org/abs/2601.09949v2 Transformers are designed for discrete tokens, yet many real-world signals are continuous processes observed through noisy sampling. Discrete tokenizations (raw values, patches, finite differences) can be brittle in low signal-to-noise regimes, especially when downstream objectives impose asymmetric penalties that rationally encourage abstention. We introduce Kinematic Tokenization, an optimization-based continuous-time representation that reconstructs an explicit spline from noisy measurements and tokenizes local spline coefficients (position, velocity, acceleration, jerk). This is applied to financial time series data in the form of asset prices in conjunction with trading volume profiles. Across a multi-asset daily-equity testbed, we use a risk-averse asymmetric classification objective as a stress test for learnability. Under this objective, several discrete baselines collapse to an absorbing cash policy (the Liquidation Equilibrium), whereas the continuous spline tokens sustain calibrated, non-trivial action distributions and stable policies. These results suggest that explicit continuous-time tokens can improve the learnability and calibration of selective decision policies in noisy time series under abstention-inducing losses. --- ### Interpolation-Based Optimization for Enforcing lp-Norm Metric Differential Privacy in Continuous and Fine-Grained Domains Authors: Chenxi Qiu Published: 2026-01-15 Categories: cs.LG, cs.CR arXiv: https://arxiv.org/abs/2601.09946v1 Metric Differential Privacy (mDP) generalizes Local Differential Privacy (LDP) by adapting privacy guarantees based on pairwise distances, enabling context-aware protection and improved utility. While existing optimization-based methods reduce utility loss effectively in coarse-grained domains, optimizing mDP in fine-grained or continuous settings remains challenging due to the computational cost of constructing dense perterubation matrices and satisfying pointwise constraints. In this paper, we propose an interpolation-based framework for optimizing lp-norm mDP in such domains. Our approach optimizes perturbation distributions at a sparse set of anchor points and interpolates distributions at non-anchor locations via log-convex combinations, which provably preserve mDP. To address privacy violations caused by naive interpolation in high-dimensional spaces, we decompose the interpolation process into a sequence of one-dimensional steps and derive a corrected formulation that enforces lp-norm mDP by design. We further explore joint optimization over perturbation distributions and privacy budget allocation across dimensions. Experiments on real-world location datasets demonstrate that our method offers rigorous privacy guarantees and competitive utility in fine-grained domains, outperforming baseline mechanisms. in high-dimensional spaces, we decompose the interpolation process into a sequence of one-dimensional steps and derive a corrected formulation that enforces lp-norm mDP by design. We further explore joint optimization over perturbation distributions and privacy budget allocation across dimensions. Experiments on real-world location datasets demonstrate that our method offers rigorous privacy guarantees and competitive utility in fine-grained domains, outperforming baseline mechanisms. --- ### Leveraging Large Language Models to Extract and Translate Medical Information in Doctors' Notes for Health Records and Diagnostic Billing Codes Authors: Peter Hartnett, Chung-Chi Huang, Sarah Hartnett, David Hartnett Published: 2026-01-14 Categories: cs.IR, cs.CL arXiv: https://arxiv.org/abs/2603.22625v1 Physician burnout in the United States has reached critical levels, driven in part by the administrative burden of Electronic Health Record (EHR) documentation and complex diagnostic codes. To relieve this strain and maintain strict patient privacy, this thesis explores an on-device, offline automatic medical coding system. The work focuses on using open-weight Large Language Models (LLMs) to extract clinical information from physician notes and translate it into ICD-10-CM diagnostic codes without reliance on cloud-based services. A privacy-focused pipeline was developed using Ollama, LangChain, and containerized environments to evaluate multiple open-weight models, including Llama 3.2, Mistral, Phi, and DeepSeek, on consumer-grade hardware. Model performance was assessed for zero-shot, few-shot, and retrieval-augmented generation (RAG) prompting strategies using a novel benchmark of synthetic medical notes. Results show that strict JSON schema enforcement achieved near 100% formatting compliance, but accurate generation of specific diagnostic codes remains challenging for smaller local models (7B-20B parameters). Contrary to common prompt-engineering guidance, few-shot prompting degraded performance through overfitting and hallucinations. While RAG enabled limited discovery of unseen codes, it frequently saturated context windows, reducing overall accuracy. The findings suggest that fully automated unsupervised coding with local open-source models is not yet reliable; instead, a human-in-the-loop assisted coding approach is currently the most practical path forward. This work contributes a reproducible local LLM architecture and benchmark dataset for privacy-preserving medical information extraction and coding. --- ### Knowledge Boundary Discovery for Large Language Models Authors: Ziquan Wang, Zhongqi Lu Published: 2026-01-14 Categories: cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2603.21022v1 We propose Knowledge Boundary Discovery (KBD), a reinforcement learning based framework to explore the knowledge boundaries of the Large Language Models (LLMs). We define the knowledge boundary by automatically generating two types of questions: (i) those the LLM can confidently answer (within-knowledge boundary) and (ii) those it cannot (beyond-knowledge boundary). Iteratively exploring and exploiting the LLM's responses to find its knowledge boundaries is challenging because of the hallucination phenomenon. To find the knowledge boundaries of an LLM, the agent interacts with the LLM under the modeling of exploring a partially observable environment. The agent generates a progressive question as the action, adopts an entropy reduction as the reward, receives the LLM's response as the observation and updates its belief states. We demonstrate that the KBD detects knowledge boundaries of LLMs by automatically finding a set of non-trivial answerable and unanswerable questions. We validate the KBD by comparing its generated knowledge boundaries with manually crafted LLM benchmark datasets. Experiments show that our KBD-generated question set is comparable to the human-generated datasets. Our approach paves a new way to evaluate LLMs. --- ### DSL-R1: From SQL to DSL for Training Retrieval Agents across Structured and Unstructured Data with Reinforcement Learning Authors: Yunhai Hu, Junwei Zhou, Yumo Cao, Yitao Long, Yiwei Xu, Qiyi Jiang, Weiyao Wang, Xiaoyu Cao, Zhen Sun, Yiran Zou, Nan Du Published: 2026-01-14 Categories: cs.IR, cs.AI, cs.DB, cs.LG arXiv: https://arxiv.org/abs/2603.21018v1 Effective retrieval in complex domains requires bridging the gap between structured metadata and unstructured content. Existing systems typically isolate these capabilities, relying on either symbolic filtering or vector similarity, failing to capture their interplay. In this work, we propose DSL-R1, a unified framework that synergizes logical reasoning with semantic matching via a novel Domain-Specific Language (DSL). By embedding vector primitives within SQL-style operators, our approach leverages the complementary strengths of symbolic precision and semantic coverage. We further introduce a reinforcement learning mechanism where rule-based execution feedback and retrieval quality rewards jointly optimize the DSL generation, balancing structural correctness and semantic alignment. Evaluations on a large-scale industrial email benchmark demonstrate that DSL-R1 achieves a +12.3% improvement in Hit@1/3, consistently outperforming decoupled baselines and establishing a robust paradigm for hybrid retrieval. --- ### LemonadeBench: Evaluating the Economic Intuition of Large Language Models in Simple Markets Authors: Aidan Vyas Published: 2026-01-14 Categories: q-fin.GN, cs.AI arXiv: https://arxiv.org/abs/2602.13209v1 We introduce LemonadeBench v0.5, a minimal benchmark for evaluating economic intuition, long-term planning, and decision-making under uncertainty in large language models (LLMs) through a simulated lemonade stand business. Models must manage inventory with expiring goods, set prices, choose operating hours, and maximize profit over a 30-day period-tasks that any small business owner faces daily. All models demonstrate meaningful economic agency by achieving profitability, with performance scaling dramatically by sophistication-from basic models earning minimal profits to frontier models capturing 70% of theoretical optimal, a greater than 10x improvement. Yet our decomposition of business efficiency across six dimensions reveals a consistent pattern: models achieve local rather than global optimization, excelling in select areas while exhibiting surprising blind spots elsewhere. --- ### Are We Truly Innovating? A Qualitative and Quantitative Study of Originality in AI Research Papers Authors: Abeer Mostafa, Thi Huyen Nguyen, Zahra Ahmadi Published: 2026-01-14 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.06054v3 Assessing originality in AI research is arguably the most consequential yet least reliable step in peer review. Reviewer judgments of originality remain opaque, inconsistent, and dependent on comparisons to prior work that are often incomplete. In this paper, we present a large-scale, data-driven qualitative and quantitative analysis of research originality based on over 100,000 peer-review reports from leading AI venues, spanning a period of rapid growth in the field. Leveraging structured, semantically retrieved prior work and signals embedded in expert reviewer assessments, we systematically characterize how originality is perceived in practice and identify the key dimensions that most strongly influence novelty judgments. Our analysis yields a fine-grained, evidence-based framework that equips both authors and reviewers with actionable insights into how originality is evaluated. In addition, we evaluate the reliability of current large language model (LLM) agents in assessing originality. We find that these models tend to systematically overestimate novelty and struggle to detect conceptual plagiarism, particularly in the presence of paraphrasing. We release our dataset, trained models, and code at: https://anonymous.4open.science/r/Novelty-Reviewer-365C/. --- ### PersonaPlex: Voice and Role Control for Full Duplex Conversational Speech Models Authors: Rajarshi Roy, Jonathan Raiman, Sang-gil Lee, Teodor-Dumitru Ene, Robert Kirby, Sungwon Kim, Jaehyeon Kim, Bryan Catanzaro Published: 2026-01-14 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.06053v1 Recent advances in duplex speech models have enabled natural, low-latency speech-to-speech interactions. However, existing models are restricted to a fixed role and voice, limiting their ability to support structured, role-driven real-world applications and personalized interactions. In this work, we introduce PersonaPlex, a duplex conversational speech model that incorporates hybrid system prompts, combining role conditioning with text prompts and voice cloning with speech samples. PersonaPlex is trained on a large-scale synthetic dataset of paired prompts and user-agent conversations, generated with open-source large language models (LLM) and text-to-speech (TTS) models. To evaluate role conditioning in real-world settings, we extend the Full-Duplex-Bench benchmark beyond a single assistant role to multi-role customer service scenarios. Experiments show that PersonaPlex achieves strong role-conditioned behavior, voice-conditioned speech, and natural conversational responsiveness, surpassing state-of-the-art duplex speech models and hybrid large language model-based speech systems in role adherence, speaker similarity, latency, and naturalness. --- ### A Survey of Agent Memory in the Second Half: Towards Self-Evolving and Long-Horizon Agents Authors: Wei-Chieh Huang, Weizhi Zhang, Yueqing Liang, Yuanchen Bei, Yankai Chen, Tao Feng, Xinyu Pan, Zhen Tan, Yu Wang, Tianxin Wei, Shanglin Wu, Ruiyao Xu et al. Published: 2026-01-14 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2602.06052v4 Research in artificial intelligence is shifting from model innovations and benchmark scores towards problem definition and rigorous real-world evaluation. As the field enters the "second half," the central challenge becomes real utility in long-horizon, dynamic, and user-dependent settings such as agentic coding, deep research, and computer use, where LLM-based agents face context explosion beyond fixed context windows and must continuously accumulate, manage, and selectively reuse information across extended interactions. Memory, with hundreds of papers released in 2025, therefore emerges as the critical solution to fill this utility gap. Beyond passive storage, memory is increasingly the substrate through which agents self-evolve: short-term memory gates which experiences are perceived and abstracted during execution, while long-term memory consolidates them into reusable knowledge and skills, forming the loop through which agents improve from their own experience. In this survey, we provide a unified view of foundation agent memory along three dimensions: memory substrate (internal parametric state and external retrieval-augmented stores), cognitive mechanism (sensory, working, episodic, semantic, and procedural), and memory subject (user-centric personalization and agent-centric experience). We then analyze how memory is operated under single- and multi-agent topologies and highlight learning policies over memory operations, showing how memory management itself is becoming a trainable capability spanning reinforcement-learned context curation, experience consolidation at decision time, and the emerging ecosystem of portable, shareable agent skills. Finally, we review evaluation benchmarks and metrics for memory utility, and outline open challenges and future directions. --- ### CAST: Character-and-Scene Episodic Memory for Agents Authors: Kexin Ma, Bojun Li, Yuhua Tang, Liting Sun, Ruochun Jin Published: 2026-01-14 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.06051v3 Episodic memory is a central component of human memory, which refers to the ability to recall coherent events grounded in who, when, and where. However, most agent memory systems only emphasize semantic recall and treat experience as structures such as key-value, vector, or graph, which makes them struggle to represent and retrieve coherent events. To address this challenge, we propose a Character-and-Scene based memory architecture(CAST) inspired by dramatic theory. Specifically, CAST constructs 3D scenes (time/place/topic) and organizes them into character profiles that summarize the events of a character to represent episodic memory. Moreover, CAST complements this episodic memory with a graph-based semantic memory, which yields a robust dual memory design. Experiments demonstrate that CAST has averagely improved 8.11% F1 and 10.21% J(LLM-as-a-Judge) than baselines on various datasets, especially on open and time-sensitive conversational questions. --- ### Relevance-aware Multi-context Contrastive Decoding for Retrieval-augmented Visual Question Answering Authors: Jongha Kim, Byungoh Ko, Jeehye Na, Jinsung Yoon, Hyunwoo J. Kim Published: 2026-01-14 Categories: cs.CL, cs.CV arXiv: https://arxiv.org/abs/2602.06050v1 Despite the remarkable capabilities of Large Vision Language Models (LVLMs), they still lack detailed knowledge about specific entities. Retrieval-augmented Generation (RAG) is a widely adopted solution that enhances LVLMs by providing additional contexts from an external Knowledge Base. However, we observe that previous decoding methods for RAG are sub-optimal as they fail to sufficiently leverage multiple relevant contexts and suppress the negative effects of irrelevant contexts. To this end, we propose Relevance-aware Multi-context Contrastive Decoding (RMCD), a novel decoding method for RAG. RMCD outputs a final prediction by combining outputs predicted with each context, where each output is weighted based on its relevance to the question. By doing so, RMCD effectively aggregates useful information from multiple relevant contexts while also counteracting the negative effects of irrelevant ones. Experiments show that RMCD consistently outperforms other decoding methods across multiple LVLMs, achieving the best performance on three knowledge-intensive visual question-answering benchmarks. Also, RMCD can be simply applied by replacing the decoding method of LVLMs without additional training. Analyses also show that RMCD is robust to the retrieval results, consistently performing the best across the weakest to the strongest retrieval results. Code is available at https://github.com/mlvlab/RMCD. --- ### ROSA-Tuning: Enhancing Long-Context Modeling via Suffix Matching Authors: Yunao Zheng, Xiaojie Wang, Lei Ren, Wei Chen Published: 2026-01-14 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.02499v2 Long-context capability and computational efficiency are among the central challenges facing today's large language models. Existing efficient attention methods reduce computational complexity, but they typically suffer from a limited coverage of the model state. This paper proposes ROSA-Tuning, a retrieval-and-recall mechanism for enhancing the long-context modeling ability of pretrained models. Beyond the standard attention mechanism, ROSA-Tuning leverages in parallel a CPU-based ROSA (RWKV Online Suffix Automaton) retrieval module, which efficiently locates historical positions in long contexts that are relevant to the current query, and injects the retrieved information into the model state in a trainable manner; subsequent weighted fusion can then be handled by range-restricted attention. To enable end-to-end training, we employ the binary discretization strategy and the counterfactual gradient algorithm, and further optimize overall execution efficiency via an asynchronous CPU-GPU pipeline. Systematic evaluations on Qwen3-Base-1.7B show that ROSA-Tuning substantially restores the long-context modeling ability of windowed-attention models, achieving performance close to and in some cases matching global attention on benchmarks such as LongBench, while maintaining computational efficiency and GPU memory usage that are nearly comparable to windowed-attention methods, offering a new technical path for efficient long-context processing. The example code can be found at https://github.com/zyaaa-ux/ROSA-Tuning. --- ### Test-Time Detoxification without Training or Learning Anything Authors: Baturay Saglam, Dionysis Kalogerias Published: 2026-01-14 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.02498v2 Large language models can produce toxic or inappropriate text even for benign inputs, creating risks when deployed at scale. Detoxification is therefore important for safety and user trust, particularly when we want to reduce harmful content without sacrificing the model's generation quality. Many existing approaches rely on model retraining, gradients, or learned auxiliary components, which can be costly and may not transfer across model families or to truly black-box settings. We introduce a test-time procedure that approximates the gradient of completion toxicity with respect to the input embeddings and uses a small number of descent steps to steer generation toward less toxic continuations. This is achieved with zeroth-order optimization that requires only access to input embeddings, a toxicity scoring function, and forward evaluations of the model. Empirically, the approach delivers robust toxicity reductions across models and prompts and, in most settings, achieves the best overall toxicity-quality trade-off. More broadly, our work positions word embeddings as effective control variables and encourages wider use of black-box optimization to guide autoregressive language models toward scalable, safer text generation, without requiring any training or access to intermediate computations. --- ### STEMVerse: A Dual-Axis Diagnostic Framework for STEM Reasoning in Large Language Models Authors: Xuzhao Li, Xuchen Li, Jian Zhao, Shiyu Hu Published: 2026-01-14 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2602.02497v1 As Large Language Models (LLMs) achieve significant breakthroughs in complex reasoning tasks, evaluating their proficiency in science, technology, engineering, and mathematics (STEM) has become a primary method for measuring machine intelligence. However, current evaluation paradigms often treat benchmarks as isolated "silos," offering only monolithic aggregate scores that neglect the intricacies of both academic specialization and cognitive depth. This result-oriented approach fails to distinguish whether model errors stem from insufficient domain knowledge or deficiencies in cognitive capacity, thereby limiting the diagnostic value. To address this, we propose STEMVerse, a diagnostic framework designed to systematically analyze the STEM reasoning capabilities of LLMs. This framework characterizes model performance across academic specialization and cognitive complexity to map the capability required for reasoning. We re-aggregate over 20,000 STEM problems from mainstream benchmarks into a unified "Discipline $\times$ Cognition" capability space, assigning dual-axis labels to every instance. Utilizing this unified diagnostic framework, we systematically evaluate representative LLM families across varying parameter scales and training paradigms. Our empirical results reveal structural failure patterns in STEM reasoning. By integrating multi-disciplinary coverage and fine-grained cognitive stratification into a unified framework, STEMVerse provides a clear and actionable perspective for understanding the scientific reasoning characteristics of LLMs. --- ### The Hypocrisy Gap: Quantifying Divergence Between Internal Belief and Chain-of-Thought Explanation via Sparse Autoencoders Authors: Shikhar Shiromani, Archie Chaudhury, Sri Pranav Kunda Published: 2026-01-14 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.02496v1 Large Language Models (LLMs) frequently exhibit unfaithful behavior, producing a final answer that differs significantly from their internal chain of thought (CoT) reasoning in order to appease the user they are conversing with. In order to better detect this behavior, we introduce the Hypocrisy Gap, a mechanistic metric utilizing Sparse Autoencoders (SAEs) to quantify the divergence between a model's internal reasoning and its final generation. By mathematically comparing an internal truth belief, derived via sparse linear probes, to the final generated trajectory in latent space, we quantify and detect a model's tendency to engage in unfaithful behavior. Experiments on Gemma, Llama, and Qwen models using Anthropic's Sycophancy benchmark show that our method achieves an AUROC of 0.55-0.73 for detecting sycophantic runs and 0.55-0.74 for hypocritical cases where the model internally "knows" the user is wrong, consistently outperforming a decision-aligned log-probability baseline (0.41-0.50 AUROC). --- ### SafeTalkCoach: Diversity-Driven Multi-Agent Simulation for Parent-Teen Health Conversations Authors: Benyamin Tabarsi, Wenbo Li, Tahreem Yasir, Aryan Santhosh Kumar, Laura Widman, Dongkuan Xu, Tiffany Barnes Published: 2026-01-14 Categories: cs.CL, cs.AI, cs.CY, cs.MA arXiv: https://arxiv.org/abs/2602.00017v1 The importance of effective parent-child communication about sexual health is widely acknowledged, but real-world data on these conversations is scarce and challenging to collect, due to their private and sensitive nature. Although LLMs have been widely adopted in dialogue generation, they may deviate from best practices and frequently lack realism and diversity. We introduce SafeTalkCoach, a diversity-driven multi-agent dialogue generation framework that simulates parent-child conversations about sexual health, and present an accompanying dataset. SafeTalkCoach integrates crowd-sourced and synthesized scenarios, established sexual health guidelines, evidence-based personas, adaptive control modules, and hierarchical diversification. Through evaluations, we demonstrate that SafeTalkCoach generates diverse conversations while maintaining realism, communication quality, and controllability in practice. Our goal is that the SafeTalkCoach framework and the dataset support both AI research and health communications practices. --- ### Rethinking LLM-Driven Heuristic Design: Generating Efficient and Specialized Solvers via Dynamics-Aware Optimization Authors: Rongzheng Wang, Yihong Huang, Muquan Li, Jiakai Li, Di Liang, Bob Simons, Pei Ke, Shuang Liang, Ke Qin Published: 2026-01-14 Categories: cs.LG, cs.AI, cs.NE arXiv: https://arxiv.org/abs/2601.20868v2 Large Language Models (LLMs) have advanced the field of Combinatorial Optimization through automated heuristic generation. Instead of relying on manual design, this LLM-Driven Heuristic Design (LHD) process leverages LLMs to iteratively generate and refine solvers to achieve high performance. However, existing LHD frameworks face two critical limitations: (1) Endpoint-only evaluation, which ranks solvers solely by final gap to a reference solution, ignoring the convergence process and runtime efficiency; (2) High adaptation costs, where distribution shifts necessitate re-adaptation to generate specialized solvers for heterogeneous instance groups. To address these issues, we propose Dynamics-Aware Solver Heuristics (DASH), a framework that co-optimizes solver search mechanisms and runtime schedules guided by a convergence-aware metric, thereby identifying efficient and high-performance solvers. Furthermore, to mitigate expensive re-adaptation, DASH incorporates Profiled Library Retrieval (PLR), which maintains group-specialized solvers for profile-aware warm starts. These solvers are archived concurrently during evolution, allowing DASH to reuse matched specialists across heterogeneous distributions without restarting adaptation. Experiments on four combinatorial optimization problems demonstrate that DASH improves runtime efficiency by over 4 times while outperforming prior LHD baselines in the overall balance between gap and runtime across diverse problem scales. Furthermore, by enabling profile-aware warm starts, DASH maintains lower gap under distribution shift while reducing LLM adaptation costs by about 90%. --- ### NavFormer: IGRF Forecasting in Moving Coordinate Frames Authors: Yoontae Hwang, Dongwoo Lee, Minseok Choi, Heechan Park, Yong Sup Ihn, Daham Kim, Deok-Young Lee Published: 2026-01-14 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2601.18800v2 Triad magnetometer components change with sensor attitude even when the IGRF total intensity target stays invariant. NavFormer forecasts this invariant target with rotation invariant scalar features and a Canonical SPD module that stabilizes the spectrum of window level second moments of the triads without sign discontinuities. The module builds a canonical frame from a Gram matrix per window and applies state dependent spectral scaling in the original coordinates. Experiments across five flights show lower error than strong baselines in standard training, few shot training, and zero shot transfer. The code is available at: https://anonymous.4open.science/r/NavFormer-Robust-IGRF-Forecasting-for-Autonomous-Navigators-0765 --- ### Private Accountability in the Age of Artificial Intelligence Authors: Sonia Katyal Published: 2026-01-14 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2601.17013v1 In this Article, I explore the impending conflict between the protection of civil rights and artificial intelligence (AI). While both areas of law have amassed rich and well-developed areas of scholarly work and doctrinal support, a growing body of scholars are interrogating the intersection between them. This Article argues that the issues surrounding algorithmic accountability demonstrate a deeper, more structural tension within a new generation of disputes regarding law and technology. As I argue, the true promise of AI does not lie in the information we reveal to one another, but rather in the questions it raises about the interaction of technology, property, and civil rights. For this reason, I argue that we are looking in the wrong place if we look only to the state to address issues of algorithmic accountability. Instead, we must turn to other ways to ensure more transparency and accountability that stem from private industry, rather than public regulation. The issue of algorithmic bias represents a crucial new world of civil rights concerns, one that is distinct in nature from the ones that preceded it. Since we are in a world where the activities of private corporations, rather than the state, are raising concerns about privacy, due process, and discrimination, we must focus on the role of private corporations in addressing the issue. Towards this end, I discuss a variety of tools to help eliminate the opacity of AI, including codes of conduct, impact statements, and whistleblower protection, which I argue carries the potential to encourage greater endogeneity in civil rights enforcement. Ultimately, by examining the relationship between private industry and civil rights, we can perhaps develop a new generation of forms of accountability in the process. --- ### Optimizing the Landscape of LLM Embeddings with Dynamic Exploratory Graph Analysis for Generative Psychometrics: A Monte Carlo Study Authors: Hudson Golino Published: 2026-01-14 Categories: cs.LG, stat.AP arXiv: https://arxiv.org/abs/2601.17010v1 Large language model (LLM) embeddings are increasingly used to estimate dimensional structure in psychological item pools prior to data collection, yet current applications treat embeddings as static, cross-sectional representations. This approach implicitly assumes uniform contribution across all embedding coordinates and overlooks the possibility that optimal structural information may be concentrated in specific regions of the embedding space. This study reframes embeddings as searchable landscapes and adapts Dynamic Exploratory Graph Analysis (DynEGA) to systematically traverse embedding coordinates, treating the dimension index as a pseudo-temporal ordering analogous to intensive longitudinal trajectories. A large-scale Monte Carlo simulation embedded items representing five dimensions of grandiose narcissism using OpenAI's text-embedding-3-small model, generating network estimations across systematically varied item pool sizes (3-40 items per dimension) and embedding depths (3-1,298 dimensions). Results reveal that Total Entropy Fit Index (TEFI) and Normalized Mutual Information (NMI) leads to competing optimization trajectories across the embedding landscape. TEFI achieves minima at deep embedding ranges (900--1,200 dimensions) where entropy-based organization is maximal but structural accuracy degrades, whereas NMI peaks at shallow depths where dimensional recovery is strongest but entropy-based fit remains suboptimal. Single-metric optimization produces structurally incoherent solutions, whereas a weighted composite criterion identifies embedding dimensions depth regions that jointly balance accuracy and organization. Optimal embedding depth scales systematically with item pool size. These findings establish embedding landscapes as non-uniform semantic spaces requiring principled optimization rather than default full-vector usage. --- ### Online parameter estimation for the Crazyflie quadcopter through an EM algorithm Authors: Yanhua Zhao Published: 2026-01-14 Categories: cs.AI, cs.RO, eess.SY arXiv: https://arxiv.org/abs/2601.17009v1 Drones are becoming more and more popular nowadays. They are small in size, low in cost, and reliable in operation. They contain a variety of sensors and can perform a variety of flight tasks, reaching places that are difficult or inaccessible for humans. Earthquakes damage a lot of infrastructure, making it impossible for rescuers to reach some areas. But drones can help. Many amateur and professional photographers like to use drones for aerial photography. Drones play a non-negligible role in agriculture and transportation too. Drones can be used to spray pesticides, and they can also transport supplies. A quadcopter is a four-rotor drone and has been studied in this paper. In this paper, random noise is added to the quadcopter system and its effects on the drone system are studied. An extended Kalman filter has been used to estimate the state based on noisy observations from the sensor. Based on a SDE system, a linear quadratic Gaussian controller has been implemented. The expectation maximization algorithm has been applied for parameter estimation of the quadcopter. The results of offline parameter estimation and online parameter estimation are presented. The results show that the online parameter estimation has a slightly larger range of convergence values than the offline parameter estimation. --- ### Bayesian Robust Financial Trading with Adversarial Synthetic Market Data Authors: Haochong Xia, Simin Li, Ruixiao Xu, Zhixia Zhang, Hongxiang Wang, Zhiqian Liu, Teng Yao Long, Molei Qin, Chuqiao Zong, Bo An Published: 2026-01-14 Categories: cs.LG, q-fin.TR arXiv: https://arxiv.org/abs/2601.17008v1 Algorithmic trading relies on machine learning models to make trading decisions. Despite strong in-sample performance, these models often degrade when confronted with evolving real-world market regimes, which can shift dramatically due to macroeconomic changes-e.g., monetary policy updates or unanticipated fluctuations in participant behavior. We identify two challenges that perpetuate this mismatch: (1) insufficient robustness in existing policy against uncertainties in high-level market fluctuations, and (2) the absence of a realistic and diverse simulation environment for training, leading to policy overfitting. To address these issues, we propose a Bayesian Robust Framework that systematically integrates a macro-conditioned generative model with robust policy learning. On the data side, to generate realistic and diverse data, we propose a macro-conditioned GAN-based generator that leverages macroeconomic indicators as primary control variables, synthesizing data with faithful temporal, cross-instrument, and macro correlations. On the policy side, to learn robust policy against market fluctuations, we cast the trading process as a two-player zero-sum Bayesian Markov game, wherein an adversarial agent simulates shifting regimes by perturbing macroeconomic indicators in the macro-conditioned generator, while the trading agent-guided by a quantile belief network-maintains and updates its belief over hidden market states. The trading agent seeks a Robust Perfect Bayesian Equilibrium via Bayesian neural fictitious self-play, stabilizing learning under adversarial market perturbations. Extensive experiments on 9 financial instruments demonstrate that our framework outperforms 9 state-of-the-art baselines. In extreme events like the COVID, our method shows improved profitability and risk management, offering a reliable solution for trading under uncertain and shifting market dynamics. --- ### Analysis of voice recordings features for Classification of Parkinson's Disease Authors: Beatriz Pérez-Sánchez, Noelia Sánchez-Maroño, Miguel A. Díaz-Freire Published: 2026-01-14 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.17007v1 Parkinson's disease (PD) is a chronic neurodegenerative disease. Early diagnosis is essential to mitigate the progressive deterioration of patients' quality of life. The most characteristic motor symptoms are very mild in the early stages, making diagnosis difficult. Recent studies have shown that the use of patient voice recordings can aid in early diagnosis. Although the analysis of such recordings is costly from a clinical point of view, advances in machine learning techniques are making the processing of this type of data increasingly accurate and efficient. Vocal recordings contain many features, but it is not known whether all of them are relevant for diagnosing the disease. This paper proposes the use of different types of machine learning models combined with feature selection methods to detect the disease. The selection techniques allow to reduce the number of features used by the classifiers by determining which ones provide the most information about the problem. The results show that machine learning methods, in particular neural networks, are suitable for PD classification and that the number of features can be significantly reduced without affecting the performance of the models. --- ### MathMixup: Boosting LLM Mathematical Reasoning with Difficulty-Controllable Data Synthesis and Curriculum Learning Authors: Xuchen Li, Jing Chen, Xuzhao Li, Hao Liang, Xiaohuan Zhou, Taifeng Wang, Wentao Zhang Published: 2026-01-14 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2601.17006v1 In mathematical reasoning tasks, the advancement of Large Language Models (LLMs) relies heavily on high-quality training data with clearly defined and well-graded difficulty levels. However, existing data synthesis methods often suffer from limited diversity and lack precise control over problem difficulty, making them insufficient for supporting efficient training paradigms such as curriculum learning. To address these challenges, we propose MathMixup, a novel data synthesis paradigm that systematically generates high-quality, difficulty-controllable mathematical reasoning problems through hybrid and decomposed strategies. Automated self-checking and manual screening are incorporated to ensure semantic clarity and a well-structured difficulty gradient in the synthesized data. Building on this, we construct the MathMixupQA dataset and design a curriculum learning strategy that leverages these graded problems, supporting flexible integration with other datasets. Experimental results show that MathMixup and its curriculum learning strategy significantly enhance the mathematical reasoning performance of LLMs. Fine-tuned Qwen2.5-7B achieves an average score of 52.6\% across seven mathematical benchmarks, surpassing previous state-of-the-art methods. These results fully validate the effectiveness and broad applicability of MathMixup in improving the mathematical reasoning abilities of LLMs and advancing data-centric curriculum learning. --- ### From Noise to Insights: Enhancing Supply Chain Decision Support through AI-Based Survey Integrity Analytics Authors: Bhubalan Mani Published: 2026-01-14 Categories: cs.CY, cs.AI, cs.ET arXiv: https://arxiv.org/abs/2601.17005v1 The reliability of survey data is crucial in supply chain decision-making, particularly when evaluating readiness for AI-driven tools such as safety stock optimization systems. However, surveys often attract low-effort or fake responses that degrade the accuracy of derived insights. This study proposes a lightweight AI-based framework for filtering unreliable survey inputs using a supervised machine learning approach. In this expanded study, a larger dataset of 99 industry responses was collected, with manual labeling to identify fake responses based on logical inconsistencies and response patterns. After preprocessing and label encoding, both Random Forest and baseline models (Logistic Regression, XGBoost) were trained to distinguish genuine from fake responses. The best-performing model achieved an 92.0% accuracy rate, demonstrating improved detection compared to the pilot study. Despite limitations, the results highlight the viability of integrating AI into survey pipelines and provide a scalable solution for improving data integrity in supply chain research, especially during product launch and technology adoption phases. --- ### Beyond Simulations: What 20,000 Real Conversations Reveal About Mental Health AI Safety Authors: Caitlin A. Stamatis, Jonah Meyerhoff, Richard Zhang, Olivier Tieleman, Matteo Malgaroli, Thomas D. Hull Published: 2026-01-14 Categories: cs.CY, cs.CL arXiv: https://arxiv.org/abs/2601.17003v2 Mental-health AI safety is typically evaluated with small, simulation-based benchmarks that may not reflect the linguistic and contextual diversity of deployment. We pair four benchmark replications with an ecological audit of real-world conversations to evaluate a purpose-built mental-health AI alongside six frontier general-purpose models spanning four families (OpenAI GPT-5, GPT-5.1, GPT-5.2; DeepSeek V3; Google Gemini 3 Flash; Moonshot Kimi K2). The purpose-built system produced significantly lower overall potentially harmful content rates than every frontier comparator on suicide/self-harm, eating-disorder, and substance-use prompts (CCDH Benchmark: Ash 6.2% vs frontier models 18.0-52.0%, all p < .001). In an audit of 20,000 deployment conversations, clinician review within the audit pipeline confirmed no suicide-risk conversations lacking crisis resources and three NSSI-related conversations without crisis intervention, a within-pipeline conditional rate of 3/800 (0.38%). To extend population-level inference, we adjudicated 600 conversations randomly sampled from the full deployment distribution via blinded clinician review. Against these labels, the LLM judge showed 100% sensitivity (6/6; 95% CI 54.1-100%) and 99.2% specificity (589/594) at its operating threshold, and the conversational model delivered crisis resources in all 6 clinician-confirmed cases (zero end-to-end false negatives; rule-of-three upper 95% CI 0.50%). Findings argue for ecological auditing as a complement to pre-deployment evaluation in mental-health AI safety --- ### RAM-SD: Retrieval-Augmented Multi-agent framework for Sarcasm Detection Authors: Ziyang Zhou, Ziqi Liu, Yan Wang, Yiming Lin, Yangbin Chen Published: 2026-01-14 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.17002v1 Sarcasm detection remains a significant challenge due to its reliance on nuanced contextual understanding, world knowledge, and multi-faceted linguistic cues that vary substantially across different sarcastic expressions. Existing approaches, from fine-tuned transformers to large language models, apply a uniform reasoning strategy to all inputs, struggling to address the diverse analytical demands of sarcasm. These demands range from modeling contextual expectation violations to requiring external knowledge grounding or recognizing specific rhetorical patterns. To address this limitation, we introduce RAM-SD, a Retrieval-Augmented Multi-Agent framework for Sarcasm Detection. The framework operates through four stages: (1) contextual retrieval grounds the query in both sarcastic and non-sarcastic exemplars; (2) a meta-planner classifies the sarcasm type and selects an optimal reasoning plan from a predefined set; (3) an ensemble of specialized agents performs complementary, multi-view analysis; and (4) an integrator synthesizes these analyses into a final, interpretable judgment with a natural language explanation. Evaluated on four standard benchmarks, RAM-SD achieves a state-of-the-art Macro-F1 of 77.74%, outperforming the strong GPT-4o+CoC baseline by 7.01 points. Our framework not only sets a new performance benchmark but also provides transparent and interpretable reasoning traces, illuminating the cognitive processes behind sarcasm comprehension. --- ### Attention Is Not Retention: The Orthogonality Constraint in Infinite-Context Architectures Authors: Oliver Zahn, Matt Beton, Simran Chana Published: 2026-01-14 Categories: q-bio.NC, cs.AI arXiv: https://arxiv.org/abs/2601.15313v2 Biological memory solves a problem that eludes current AI: storing specific episodic facts without corrupting general semantic knowledge. Complementary Learning Systems theory explains this through two subsystems - a fast hippocampal system using sparse, pattern-separated representations for episodes, and a slow neocortical system using distributed representations for statistical regularities. Current AI systems lack this separation, attempting to serve both functions through neural weights alone. We identify the Orthogonality Constraint: reliable memory requires orthogonal keys, but semantic embeddings cannot be orthogonal because training clusters similar concepts together. The result is Semantic Interference (connecting to what cognitive psychologists have long observed in human memory), where neural systems writing facts into shared continuous parameters collapse to near-random accuracy within tens of semantically related facts. Through semantic density (rho), the mean pairwise cosine similarity, we show collapse occurs at N=5 facts (rho > 0.6) or N ~ 20-75 (moderate rho). We validate across modalities: 16,309 Wikipedia facts, scientific measurements (rho = 0.96, 0.02% accuracy at N=10,000), and image embeddings (rho = 0.82, 0.05% at N=2,000). This failure is geometric - no increase in model capacity can overcome interference when keys share semantic overlap. We propose Knowledge Objects (KOs): structured facts with hash-based identity, controlled vocabularies, and explicit version chains. On Wikipedia facts, KO retrieval achieves 45.7% where Modern Hopfield Networks collapse to near-zero; hash-based retrieval maintains 100%. Production systems (Claude Memory, ChatGPT Memory) store unstructured text, causing schema drift (40-70% consistency) and version ambiguity. Knowledge Objects provide the discrete hippocampal component that enables reliable bicameral memory. --- ### Do people expect different behavior from large language models acting on their behalf? Evidence from norm elicitations in two canonical economic games Authors: Paweł Niszczota, Elia Antoniou Published: 2026-01-14 Categories: cs.GT, cs.AI, cs.CL, cs.CY, cs.HC, econ.GN arXiv: https://arxiv.org/abs/2601.15312v1 While delegating tasks to large language models (LLMs) can save people time, there is growing evidence that offloading tasks to such models produces social costs. We use behavior in two canonical economic games to study whether people have different expectations when decisions are made by LLMs acting on their behalf instead of themselves. More specifically, we study the social appropriateness of a spectrum of possible behaviors: when LLMs divide resources on our behalf (Dictator Game and Ultimatum Game) and when they monitor the fairness of splits of resources (Ultimatum Game). We use the Krupka-Weber norm elicitation task to detect shifts in social appropriateness ratings. Results of two pre-registered and incentivized experimental studies using representative samples from the UK and US (N = 2,658) show three key findings. First, people find that offers from machines - when no acceptance is necessary - are judged to be less appropriate than when they come from humans, although there is no shift in the modal response. Second - when acceptance is necessary - it is more appropriate for a person to reject offers from machines than from humans. Third, receiving a rejection of an offer from a machine is no less socially appropriate than receiving the same rejection from a human. Overall, these results suggest that people apply different norms for machines deciding on how to split resources but are not opposed to machines enforcing the norms. The findings are consistent with offers made by machines now being viewed as having both a cognitive and emotional component. --- ### Aeon: High-Performance Neuro-Symbolic Memory Management for Long-Horizon LLM Agents Authors: Mustafa Arslan Published: 2026-01-14 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.15311v3 Large Language Models (LLMs) are fundamentally constrained by the quadratic computational cost of self-attention and the "Lost in the Middle" phenomenon, where reasoning capabilities degrade as context windows expand. Existing solutions, primarily "Flat RAG" architectures relying on vector databases, treat memory as an unstructured bag of embeddings, failing to capture the hierarchical and temporal structure of long-horizon interactions. This paper presents Aeon, a Neuro-Symbolic Cognitive Operating System that redefines memory as a managed OS resource. Aeon structures memory into a Memory Palace (a spatial index implemented via Atlas, a SIMD-accelerated Page-Clustered Vector Index) and a Trace (a neuro-symbolic episodic graph). This architecture introduces three advances: (1) Symmetric INT8 Scalar Quantization, achieving 3.1x spatial compression and 5.6x math acceleration via NEON SDOT intrinsics; (2) a decoupled Write-Ahead Log (WAL) ensuring crash-recoverability with statistically negligible overhead (<1%); and (3) a Sidecar Blob Arena eliminating the prior 440-character text ceiling via an append-only mmap-backed blob file with generational garbage collection. The Semantic Lookaside Buffer (SLB) exploits conversational locality to achieve sub-5us retrieval latencies, with INT8 vectors dequantized to FP32 on cache insertion to preserve L1-resident lookup performance. Benchmarks on Apple M4 Max demonstrate that the combined architecture achieves 4.70ns INT8 dot product latency, 3.09us tree traversal at 100K nodes (3.4x over FP32), and P99 read latency of 750ns under hostile 16-thread contention via epoch-based reclamation. --- ### Project Aletheia: Verifier-Guided Distillation of Backtracking for Small Language Models Authors: Aradhya Dixit, Tianxi Liang, Jai Telang Published: 2026-01-14 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.14290v1 Small Language Models (SLMs, under 10B parameters) are attractive for private, on-device deployment, yet they frequently fail on strict constraint-satisfaction problems due to linear, overconfident reasoning traces that do not recover from early mistakes. We introduce Verifier-Guided Distillation, a training protocol that transfers the process of error repair - explicit conflict detection and backtracking - rather than only correct final answers. By training a 7B model on verified reasoning traces that include mistakes and self-corrections, we show that latent verification behavior can emerge in small models, enabling them to occasionally stop, detect contradictions, and revise earlier assumptions. --- ### RPC-Bench: A Fine-grained Benchmark for Research Paper Comprehension Authors: Yelin Chen, Fanjin Zhang, Suping Sun, Yunhe Pang, Yuanchun Wang, Jian Song, Xiaoyan Li, Lei Hou, Shu Zhao, Jie Tang, Juanzi Li Published: 2026-01-14 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2601.14289v2 Understanding research papers remains challenging for foundation models due to specialized scientific discourse and complex figures and tables, yet existing benchmarks offer limited fine-grained evaluation at scale. To address this gap, we introduce RPC-Bench, a large-scale question-answering benchmark built from review-rebuttal exchanges of high-quality computer science papers, containing 15K human-verified QA pairs. We design a fine-grained taxonomy aligned with the scientific research flow to assess models' ability to understand and answer why, what, and how questions in scholarly contexts. We also define an elaborate LLM-human interaction annotation framework to support large-scale labeling and quality control. Following the LLM-as-a-Judge paradigm, we develop a scalable framework that evaluates models on correctness-completeness and conciseness, with high agreement to human judgment. Experiments reveal that even the strongest models (GPT-5) achieve only 68.2% correctness-completeness, dropping to 37.46% after conciseness adjustment, highlighting substantial gaps in precise academic paper understanding. Our code and data are available at https://rpc-bench.github.io/. --- ### DeepInflation: an AI agent for research and model discovery of inflation Authors: Ze-Yu Peng, Hao-Shi Yuan, Qi Lai, Jun-Qian Jiang, Gen Ye, Jun Zhang, Yun-Song Piao Published: 2026-01-14 Categories: astro-ph.CO, cs.AI, cs.CE, gr-qc, hep-th arXiv: https://arxiv.org/abs/2601.14288v2 We present DeepInflation, an AI agent designed for research and model discovery in inflationary cosmology. Built upon a multi-agent architecture, DeepInflation integrates Large Language Models (LLMs) with a symbolic regression (SR) engine and a retrieval-augmented generation (RAG) knowledge base. This framework enables the agent to automatically explore and verify the vast landscape of inflationary potentials while grounding its outputs in established theoretical literature. We demonstrate that DeepInflation can successfully discover simple and viable single-field slow-roll inflationary potentials consistent with the latest observations (with the ACT DR6 results taken as an example) or any given $n_s$ and $r$, and provide accurate theoretical context for obscure inflationary scenarios. DeepInflation serves as a prototype for a new generation of autonomous scientific discovery engines in cosmology, which enables researchers and non-experts alike to explore the inflationary landscape using natural language. This agent is available at https://github.com/pengzy-cosmo/DeepInflation. --- ### Chain-of-Memory: Lightweight Memory Construction with Dynamic Evolution for LLM Agents Authors: Xiucheng Xu, Bingbing Xu, Xueyun Tian, Zihe Huang, Rongxin Chen, Yunfan Li, Huawei Shen Published: 2026-01-14 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.14287v2 External memory systems are pivotal for enabling Large Language Model (LLM) agents to maintain persistent knowledge and perform long-horizon decision-making. Existing paradigms typically follow a two-stage process: computationally expensive memory construction (e.g., structuring data into graphs) followed by naive retrieval-augmented generation. However, our empirical analysis reveals two fundamental limitations: complex construction incurs high costs with marginal performance gains, and simple context concatenation fails to bridge the gap between retrieval recall and reasoning accuracy. To address these challenges, we propose CoM (Chain-of-Memory), a novel framework that advocates for a paradigm shift toward lightweight construction paired with sophisticated utilization. CoM introduces a Chain-of-Memory mechanism that organizes retrieved fragments into coherent inference paths through dynamic evolution, utilizing adaptive truncation to prune irrelevant noise. Extensive experiments on the LongMemEval and LoCoMo benchmarks demonstrate that CoM outperforms strong baselines with accuracy gains of 7.5%-10.4%, while drastically reducing computational overhead to approximately 2.7% of token consumption and 6.0% of latency compared to complex memory architectures. --- ### GNN-based Path-aware multi-view Circuit Learning for Technology Mapping Authors: Wentao Jiang, Jingxin Wang, Zhang Hu, Zhengyuan Shi, Chengyu Ma, Qiang Xu, Weikang Qian, Zhufei Chu Published: 2026-01-14 Categories: cs.ET, cs.LG arXiv: https://arxiv.org/abs/2601.14286v2 Traditional technology mapping suffers from systemic inaccuracies in delay estimation due to its reliance on abstract, technology-agnostic delay models that fail to capture the nuanced timing behavior behavior of real post-mapping circuits. To address this fundamental limitation, we introduce GPA(graph neural network (GNN)-based Path-Aware multi-view circuit learning), a novel GNN framework that learns precise, data-driven delay predictions by synergistically fusing three complementary views of circuit structure: And-Inverter Graphs (AIGs)-based functional encoding, post-mapping technology emphasizes critical timing paths. Trained exclusively on real cell delays extracted from critical paths of industrial-grade post-mapping netlists, GPA learns to classify cut delays with unprecedented accuracy, directly informing smarter mapping decisions. Evaluated on the 19 EPFL combinational benchmarks, GPA achieves 19.9%, 2.1% and 4.1% average delay reduction over the conventional heuristics methods (techmap, MCH) and the prior state-of-the-art ML-based approach SLAP, respectively-without compromising area efficiency. --- ### IMSAHLO: Integrating Multi-Scale Attention and Hybrid Loss Optimization Framework for Robust Neuronal Brain Cell Segmentation Authors: Ujjwal Jain, Oshin Misra, Roshni Chakraborty, Mahua Bhattacharya Published: 2026-01-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.11645v1 Accurate segmentation of neuronal cells in fluorescence microscopy is a fundamental task for quantitative analysis in computational neuroscience. However, it is significantly impeded by challenges such as the coexistence of densely packed and sparsely distributed cells, complex overlapping morphologies, and severe class imbalance. Conventional deep learning models often fail to preserve fine topological details or accurately delineate boundaries under these conditions. To address these limitations, we propose a novel deep learning framework, IMSAHLO (Integrating Multi-Scale Attention and Hybrid Loss Optimization), for robust and adaptive neuronal segmentation. The core of our model features Multi-Scale Dense Blocks (MSDBs) to capture features at various receptive fields, effectively handling variations in cell density, and a Hierarchical Attention (HA) mechanism that adaptively focuses on salient morphological features to preserve Region of Interest (ROI) boundary details. Furthermore, we introduce a novel hybrid loss function synergistically combining Tversky and Focal loss to combat class imbalance, alongside a topology-aware Centerline Dice (clDice) loss and a Contour-Weighted Boundary loss to ensure topological continuity and precise separation of adjacent cells. Large-scale experiments on the public Fluorescent Neuronal Cells (FNC) dataset demonstrate that our framework outperforms state-of-the-art architectures, achieving precision of 81.4%, macro F1 score of 82.7%, micro F1 score of 83.3%, and balanced accuracy of 99.5% on difficult dense and sparse cases. Ablation studies validate the synergistic benefits of multi-scale attention and hybrid loss terms. This work establishes a foundation for generalizable segmentation models applicable to a wide range of biomedical imaging modalities, pushing AI-assisted analysis toward high-throughput neurobiological pipelines. --- ### Predicting When to Trust Vision-Language Models for Spatial Reasoning Authors: Muhammad Imran, Yugyung Lee Published: 2026-01-14 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2601.11644v1 Vision-Language Models (VLMs) demonstrate impressive capabilities across multimodal tasks, yet exhibit systematic spatial reasoning failures, achieving only 49% (CLIP) to 54% (BLIP-2) accuracy on basic directional relationships. For safe deployment in robotics and autonomous systems, we need to predict when to trust VLM spatial predictions rather than accepting all outputs. We propose a vision-based confidence estimation framework that validates VLM predictions through independent geometric verification using object detection. Unlike text-based approaches relying on self-assessment, our method fuses four signals via gradient boosting: geometric alignment between VLM claims and coordinates, spatial ambiguity from overlap, detection quality, and VLM internal uncertainty. We achieve 0.674 AUROC on BLIP-2 (34.0% improvement over text-based baselines) and 0.583 AUROC on CLIP (16.1% improvement), generalizing across generative and classification architectures. Our framework enables selective prediction: at 60% target accuracy, we achieve 61.9% coverage versus 27.6% baseline (2.2x improvement) on BLIP-2. Feature analysis reveals vision-based signals contribute 87.4% of model importance versus 12.7% from VLM confidence, validating that external geometric verification outperforms self-assessment. We demonstrate reliable scene graph construction where confidence-based pruning improves precision from 52.1% to 78.3% while retaining 68.2% of edges. --- ### Syllabic Agglutinative Tokenizations for Indonesian LLM: A Study from Gasing Literacy Learning System Authors: H. Situngkir, A. B. Lumbantobing, Y. Surya Published: 2026-01-14 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2601.11643v1 This paper presents a novel syllable-based tokenization approach for Indonesian large language models, inspired by the Gasing Literacy Learning System's pedagogical methodology. Drawing on information-theoretic principles, we develop a tokenization framework that segments Indonesian text at syllable boundaries before applying byte-pair encoding, creating a vocabulary that aligns with the language's morphophonological structure. Our approach first identifies high-frequency syllables through rule-based segmentation, then constructs a compact vocabulary of 3,500 tokens that preserves meaningful linguistic units while maintaining coverage through character-level fallback. Empirical evaluation on Indonesian Wikipedia and folklore corpora from Indonesian Culture Digital Library (PDBI) demonstrates substantial improvements over conventional tokenization methods: the syllable-based approach achieves Rényi efficiency of 0.74 compared to 0.50-0.64 for pretrained multilingual tokenizers, while maintaining higher average token lengths (3.67 characters versus 2.72 for GPT-2) despite using a vocabulary an order of magnitude smaller. These gains emerge from the method's ability to internalize character-level dependencies within syllable units, reducing the computational burden on language models while respecting Indonesian's agglutinative morphology. We call the LLM built upon this principle, TOBA LLM (Tokenisasi Optimum Berbasis Aglutinasi), the convergence of human literacy pedagogy with computational optimization principles offers a promising paradigm for developing linguistically-informed tokenization strategies, particularly for morphologically rich and underrepresented languages in natural language processing. --- ### PSSF: Early osteoarthritis detection using physical synthetic knee X-ray scans and AI radiomics models Authors: Abbas Alzubaidi, Ali Al-Bayaty Published: 2026-01-14 Categories: cs.CV, cs.LG, eess.IV arXiv: https://arxiv.org/abs/2601.11642v1 Knee osteoarthritis (OA) is a major cause of disability worldwide and is still largely assessed using subjective radiographic grading, most commonly the Kellgren-Lawrence (KL) scale. Artificial intelligence (AI) and radiomics offer quantitative tools for OA assessment but depend on large, well-annotated image datasets, mainly X-ray scans, that are often difficult to obtain because of privacy, governance and resourcing constraints. In this research, we introduce a physics-based synthetic simulation framework (PSSF) to fully generate controllable X-ray scans without patients' involvement and violating their privacy and institutional constraints. This PSSF is a 2D X-ray projection simulator of anteroposterior knee radiographs from a parametric anatomical model of the distal femur and proximal tibia. Using PSSF, we create a virtual cohort of 180 subjects (260 knees), each is imaged under three protocols (reference, low-dose, and geometry-shift). Medial joint regions are automatically localized, preprocessed, and processed with the Image Biomarker Standardisation Initiative (IBSI). Practically, three machine learning (ML) models are utilized, logistic regression, random forest, and gradient boosting, to train binary (KL-like "0" vs. "2") and three-class (0-2) prediction radiographic images. Robustness is assessed within IBSI protocol, cross-protocol, and multi-protocol scenarios. Finally, features stability is then evaluated using intraclass correlation coefficients across acquisition changes. --- ### Mixture of Distributions Matters: Dynamic Sparse Attention for Efficient Video Diffusion Transformers Authors: Yuxi Liu, Yipeng Hu, Zekun Zhang, Kunze Jiang, Kun Yuan Published: 2026-01-14 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2601.11641v3 While Diffusion Transformers (DiTs) have achieved notable progress in video generation, this long-sequence generation task remains constrained by the quadratic complexity inherent to self-attention mechanisms, creating significant barriers to practical deployment. Although sparse attention methods attempt to address this challenge, existing approaches either rely on oversimplified static patterns or require computationally expensive sampling operations to achieve dynamic sparsity, resulting in inaccurate pattern predictions and degraded generation quality. To overcome these limitations, we propose a \underline{\textbf{M}}ixture-\underline{\textbf{O}}f-\underline{\textbf{D}}istribution \textbf{DiT} (\textbf{MOD-DiT}), a novel sampling-free dynamic attention framework that accurately models evolving attention patterns through a two-stage process. First, MOD-DiT leverages prior information from early denoising steps and adopts a {distributed mixing approach} to model an efficient linear approximation model, which is then used to predict mask patterns for a specific denoising interval. Second, an online block masking strategy dynamically applies these predicted masks while maintaining historical sparsity information, eliminating the need for repetitive sampling operations. Extensive evaluations demonstrate consistent acceleration and quality improvements across multiple benchmarks and model architectures, validating MOD-DiT's effectiveness for efficient, high-quality video generation while overcoming the computational limitations of traditional sparse attention approaches. --- ### Confident Learning for Object Detection under Model Constraints Authors: Yingda Yu, Jiaqi Xuan, Shuhui Shi, Xuanyu Teng, Shuyang Xu, Guanchao Tong Published: 2026-01-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.11640v1 Agricultural weed detection on edge devices is subject to strict constraints on model capacity, computational resources, and real-time inference latency, which prevent performance improvements through model scaling or ensembling. This paper proposes Model-Driven Data Correction (MDDC), a data-centric framework that enhances detection performance by iteratively diagnosing and correcting data quality deficiencies. An automated error analysis procedure categorizes detection failures into four types: false negatives, false positives, class confusion, and localization errors. These error patterns are systematically addressed through a structured train-fix-retrain pipeline with version-controlled data management. Experimental results on multiple weed detection datasets demonstrate consistent improvements of 5-25 percent in mAP at 0.5 using a fixed lightweight detector (YOLOv8n), indicating that systematic data quality optimization can effectively alleviate performance bottlenecks under fixed model capacity constraints. --- ### Global Optimization By Gradient From Hierarchical Score-Matching Spaces Authors: Ming Li Published: 2026-01-14 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.11639v3 Gradient-based methods are widely used to solve various optimization problems, however, they are either constrained by local optima dilemmas, simple convex constraints, and continuous differentiability requirements, or limited to low-dimensional simple problems. This work solve these limitations and restrictions by unifying all optimization problems with various complex constraints as a general hierarchical optimization objective without constraints, which is optimized by gradient obtained through score matching. The proposed method is verified through simple-constructed and complex-practical experiments. Even more importantly, it reveals the profound connection between global optimization and diffusion based generative modeling. --- ### Verifying Physics-Informed Neural Network Fidelity using Classical Fisher Information from Differentiable Dynamical System Authors: Josafat Ribeiro Leal Filho, Antônio Augusto Fröhlich Published: 2026-01-14 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2601.11638v1 Physics-Informed Neural Networks (PINNs) have emerged as a powerful tool for solving differential equations and modeling physical systems by embedding physical laws into the learning process. However, rigorously quantifying how well a PINN captures the complete dynamical behavior of the system, beyond simple trajectory prediction, remains a challenge. This paper proposes a novel experimental framework to address this by employing Fisher information for differentiable dynamical systems, denoted $g_F^C$. This Fisher information, distinct from its statistical counterpart, measures inherent uncertainties in deterministic systems, such as sensitivity to initial conditions, and is related to the phase space curvature and the net stretching action of the state space evolution. We hypothesize that if a PINN accurately learns the underlying dynamics of a physical system, then the Fisher information landscape derived from the PINN's learned equations of motion will closely match that of the original analytical model. This match would signify that the PINN has achieved comprehensive fidelity capturing not only the state evolution but also crucial geometric and stability properties. We outline an experimental methodology using the dynamical model of a car to compute and compare $g_F^C$ for both the analytical model and a trained PINN. The comparison, based on the Jacobians of the respective system dynamics, provides a quantitative measure of the PINN's fidelity in representing the system's intricate dynamical characteristics. --- ### Evaluating Self-Correcting Vision Agents Through Quantitative and Qualitative Metrics Authors: Aradhya Dixit Published: 2026-01-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.11637v1 Recent progress in multimodal foundation models has enabled Vision-Language Agents (VLAs) to decompose complex visual tasks into executable tool-based plans. While recent benchmarks have begun to evaluate iterative self-correction, its quantitative limits and dominant reasoning bottlenecks remain poorly characterized. This work introduces a Diagnostic Micro-Benchmark. Our analysis decouples Task Success Rate (TSR = 62 percent) from Correction Success Rate (CSR = 25 to 33 percent), revealing that initial competence does not predict repair ability. We explicitly quantify the diminishing returns of correction, which saturates after three retries. Our Failure Taxonomy reveals a frequent factor is Semantic Drift (about 28 percent of failures), a loss of contextual state. By isolating this reasoning bottleneck, this benchmark defines a reproducible framework toward stateful, trustworthy multimodal agents. --- ### Now You See Me, Now You Don't: A Unified Framework for Expression Consistent Anonymization in Talking Head Videos Authors: Anil Egin, Andrea Tangherloni, Antitza Dantcheva Published: 2026-01-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.11635v1 Face video anonymization is aimed at privacy preservation while allowing for the analysis of videos in a number of computer vision downstream tasks such as expression recognition, people tracking, and action recognition. We propose here a novel unified framework referred to as Anon-NET, streamlined to de-identify facial videos, while preserving age, gender, race, pose, and expression of the original video. Specifically, we inpaint faces by a diffusion-based generative model guided by high-level attribute recognition and motion-aware expression transfer. We then animate deidentified faces by video-driven animation, which accepts the de-identified face and the original video as input. Extensive experiments on the datasets VoxCeleb2, CelebV-HQ, and HDTF, which include diverse facial dynamics, demonstrate the effectiveness of AnonNET in obfuscating identity while retaining visual realism and temporal consistency. The code of AnonNet will be publicly released. --- ### When Rules Fall Short: Agent-Driven Discovery of Emerging Content Issues in Short Video Platforms Authors: Chenghui Yu, Hongwei Wang, Junwen Chen, Zixuan Wang, Bingfeng Deng, Zhuolin Hao, Hongyu Xiong, Yang Song Published: 2026-01-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.11634v1 Trends on short-video platforms evolve at a rapid pace, with new content issues emerging every day that fall outside the coverage of existing annotation policies. However, traditional human-driven discovery of emerging issues is too slow, which leads to delayed updates of annotation policies and poses a major challenge for effective content governance. In this work, we propose an automatic issue discovery method based on multimodal LLM agents. Our approach automatically recalls short videos containing potential new issues and applies a two-stage clustering strategy to group them, with each cluster corresponding to a newly discovered issue. The agent then generates updated annotation policies from these clusters, thereby extending coverage to these emerging issues. Our agent has been deployed in the real system. Both offline and online experiments demonstrate that this agent-based method significantly improves the effectiveness of emerging-issue discovery (with an F1 score improvement of over 20%) and enhances the performance of subsequent issue governance (reducing the view count of problematic videos by approximately 15%). More importantly, compared to manual issue discovery, it greatly reduces time costs and substantially accelerates the iteration of annotation policies. --- ### Beyond Accuracy: Evaluating Grounded Visual Evidence in Thinking with Images Authors: Xuchen Li, Xuzhao Li, Renjie Pi, Shiyu Hu, Jian Zhao, Jiahui Gao Published: 2026-01-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.11633v1 Despite the remarkable progress of Vision-Language Models (VLMs) in adopting "Thinking-with-Images" capabilities, accurately evaluating the authenticity of their reasoning process remains a critical challenge. Existing benchmarks mainly rely on outcome-oriented accuracy, lacking the capability to assess whether models can accurately leverage fine-grained visual cues for multi-step reasoning. To address these limitations, we propose ViEBench, a process-verifiable benchmark designed to evaluate faithful visual reasoning. Comprising 200 multi-scenario high-resolution images with expert-annotated visual evidence, ViEBench uniquely categorizes tasks by difficulty into perception and reasoning dimensions, where reasoning tasks require utilizing localized visual details with prior knowledge. To establish comprehensive evaluation criteria, we introduce a dual-axis matrix that provides fine-grained metrics through four diagnostic quadrants, enabling transparent diagnosis of model behavior across varying task complexities. Our experiments yield several interesting observations: (1) VLMs can sometimes produce correct final answers despite grounding on irrelevant regions, and (2) they may successfully locate the correct evidence but still fail to utilize it to reach accurate conclusions. Our findings demonstrate that ViEBench can serve as a more explainable and practical benchmark for comprehensively evaluating the effectiveness agentic VLMs. The codes will be released at: https://github.com/Xuchen-Li/ViEBench. --- ### KG-ViP: Bridging Knowledge Grounding and Visual Perception in Multi-modal LLMs for Visual Question Answering Authors: Zhiyang Li, Ao Ke, Yukun Cao, Xike Xie Published: 2026-01-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.11632v3 Multi-modal Large Language Models (MLLMs) for Visual Question Answering (VQA) often suffer from dual limitations: knowledge hallucination and insufficient fine-grained visual perception. Crucially, we identify that commonsense graphs and scene graphs provide precisely complementary solutions to these respective deficiencies by providing rich external knowledge and capturing fine-grained visual details. However, prior works typically treat them in isolation, overlooking their synergistic potential. To bridge this gap, we propose KG-ViP, a unified framework that empowers MLLMs by fusing scene graphs and commonsense graphs. The core of the KG-ViP framework is a novel retrieval-and-fusion pipeline that utilizes the query as a semantic bridge to progressively integrate both graphs, synthesizing a unified structured context that facilitates reliable multi-modal reasoning. Extensive experiments on FVQA 2.0+ and MVQA benchmarks demonstrate that KG-ViP significantly outperforms existing VQA methods. --- ### Compress to Focus: Efficient Coordinate Compression for Policy Optimization in Multi-Turn GUI Agents Authors: Yurun Song, Jiong Yin, Rongjunchen Zhang, Ian G. Harris Published: 2026-01-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.11631v1 Multi-turn GUI agents enable complex task completion through sequential decision-making, but suffer from severe context inflation as interaction history accumulates. Existing strategies either sacrifice long-term context via truncation or compromise spatial structure through token pruning. In this paper, we propose Coordinate Compression Policy Optimization (CCPO), an efficient policy optimization framework that couples visual compression with policy optimization for multi-turn GUI agents. CCPO introduces Coordinate-Aware Spatial Compression (CASC), which aggregates coordinates from multiple rollouts to capture target-relevant regions and progressively narrow historical attention around key visual areas. From interactions across rollouts, CASC adaptively constructs attention boundaries that concentrate computation on the most informative regions of the scene. We further design a Distance-Based Advantage that provides fine-grained learning signals based on distance rather than binary correctness, improving both grounding accuracy and compression quality. Extensive experiments demonstrate that CCPO achieves SOTA performance across four benchmarks with up to 55% token compression and 3.8$\times$ training speedup. --- ### A one-step generation model with a Single-Layer Transformer: Layer number re-distillation of FreeFlow Authors: Haonan Wei, Linyuan Wang, Nuolin Sun, Zhizhong Zheng, Lei Li, Bin Yan Published: 2026-01-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.11630v1 Currently, Flow matching methods aim to compress the iterative generation process of diffusion models into a few or even a single step, with MeanFlow and FreeFlow being representative achievements of one-step generation based on Ordinary Differential Equations (ODEs). We observe that the 28-layer Transformer architecture of FreeFlow can be characterized as an Euler discretization scheme for an ODE along the depth axis, where the layer index serves as the discrete time step. Therefore, we distill the number of layers of the FreeFlow model, following the same derivation logic as FreeFlow, and propose SLT (Single-Layer Transformer), which uses a single shared DiT block to approximate the depth-wise feature evolution of the 28-layer teacher. During training, it matches the teacher's intermediate features at several depth patches, fuses those patch-level representations, and simultaneously aligns the teacher's final velocity prediction. Through distillation training, we compress the 28 independent Transformer Blocks of the teacher model DiT-XL/2 into a single Transformer Block, reducing the parameter count from 675M to 4.3M. Furthermore, leveraging its minimal parameters and rapid sampling speed, SLT can screen more candidate points in the noise space within the same timeframe, thereby selecting higher-quality initial points for the teacher model FreeFlow and ultimately enhancing the quality of generated images. Experimental results demonstrate that within a time budget comparable to two random samplings of the teacher model, our method performs over 100 noise screenings and produces a high-quality sample through the teacher model using the selected points. Quality fluctuations caused by low-quality initial noise under a limited number of FreeFlow sampling calls are effectively avoided, substantially improving the stability and average generation quality of one-step generation. ---