# Research Papers — 2026-01 · bundle page 176 of 189 > Full-text markdown of papers #8751–8800 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/176 [← Previous bundle](https://aipod.dev/papers/archive/2026-01/page/175.md) [Next bundle →](https://aipod.dev/papers/archive/2026-01/page/177.md) ### Query-Document Dense Vectors for LLM Relevance Judgment Bias Analysis Authors: Samaneh Mohtadi, Gianluca Demartini Published: 2026-01-05 Categories: cs.IR, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2601.01751v1 Large Language Models (LLMs) have been used as relevance assessors for Information Retrieval (IR) evaluation collection creation due to reduced cost and increased scalability as compared to human assessors. While previous research has looked at the reliability of LLMs as compared to human assessors, in this work, we aim to understand if LLMs make systematic mistakes when judging relevance, rather than just understanding how good they are on average. To this aim, we propose a novel representational method for queries and documents that allows us to analyze relevance label distributions and compare LLM and human labels to identify patterns of disagreement and localize systematic areas of disagreement. We introduce a clustering-based framework that embeds query-document (Q-D) pairs into a joint semantic space, treating relevance as a relational property. Experiments on TREC Deep Learning 2019 and 2020 show that systematic disagreement between humans and LLMs is concentrated in specific semantic clusters rather than distributed randomly. Query-level analyses reveal recurring failures, most often in definition-seeking, policy-related, or ambiguous contexts. Queries with large variation in agreement across their clusters emerge as disagreement hotspots, where LLMs tend to under-recall relevant content or over-include irrelevant material. This framework links global diagnostics with localized clustering to uncover hidden weaknesses in LLM judgments, enabling bias-aware and more reliable IR evaluation. --- ### MANGO:Natural Multi-speaker 3D Talking Head Generation via 2D-Lifted Enhancement Authors: Lei Zhu, Lijian Lin, Ye Zhu, Jiahao Wu, Xuehan Hou, Yu Li, Yunfei Liu, Jie Chen Published: 2026-01-05 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.01749v1 Current audio-driven 3D head generation methods mainly focus on single-speaker scenarios, lacking natural, bidirectional listen-and-speak interaction. Achieving seamless conversational behavior, where speaking and listening states transition fluidly remains a key challenge. Existing 3D conversational avatar approaches rely on error-prone pseudo-3D labels that fail to capture fine-grained facial dynamics. To address these limitations, we introduce a novel two-stage framework MANGO, which leveraging pure image-level supervision by alternately training to mitigate the noise introduced by pseudo-3D labels, thereby achieving better alignment with real-world conversational behaviors. Specifically, in the first stage, a diffusion-based transformer with a dual-audio interaction module models natural 3D motion from multi-speaker audio. In the second stage, we use a fast 3D Gaussian Renderer to generate high-fidelity images and provide 2D-level photometric supervision for the 3D motions through alternate training. Additionally, we introduce MANGO-Dialog, a high-quality dataset with over 50 hours of aligned 2D-3D conversational data across 500+ identities. Extensive experiments demonstrate that our method achieves exceptional accuracy and realism in modeling two-person 3D dialogue motion, significantly advancing the fidelity and controllability of audio-driven talking heads. --- ### Crafting Adversarial Inputs for Large Vision-Language Models Using Black-Box Optimization Authors: Jiwei Guan, Haibo Jin, Haohan Wang Published: 2026-01-05 Categories: cs.CR, cs.AI, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2601.01747v4 Recent advancements in Large Vision-Language Models (LVLMs) have shown groundbreaking capabilities across diverse multimodal tasks. However, these models remain vulnerable to adversarial jailbreak attacks, where adversaries craft subtle perturbations to bypass safety mechanisms and trigger harmful outputs. Existing white-box attacks methods require full model accessibility, suffer from computing costs and exhibit insufficient adversarial transferability, making them impractical for real-world, black-box settings. To address these limitations, we propose a black-box jailbreak attack on LVLMs via Zeroth-Order optimization using Simultaneous Perturbation Stochastic Approximation (ZO-SPSA). ZO-SPSA provides three key advantages: (i) gradient-free approximation by input-output interactions without requiring model knowledge, (ii) model-agnostic optimization without the surrogate model and (iii) lower resource requirements with reduced GPU memory consumption. We evaluate ZO-SPSA on three LVLMs, including InstructBLIP, LLaVA and MiniGPT-4, achieving the highest jailbreak success rate of 83.0% on InstructBLIP, while maintaining imperceptible perturbations comparable to white-box methods. Moreover, adversarial examples generated from MiniGPT-4 exhibit strong transferability to other LVLMs, with ASR reaching 64.18%. These findings underscore the real-world feasibility of black-box jailbreaks and expose critical weaknesses in the safety mechanisms of current LVLMs --- ### Crafting Adversarial Inputs for Large Vision-Language Models Using Black-Box Optimization Authors: Jiwei Guan, Haibo Jin, Haohan Wang Published: 2026-01-05 Categories: cs.CR, cs.AI, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2601.01747v1 Recent advancements in Large Vision-Language Models (LVLMs) have shown groundbreaking capabilities across diverse multimodal tasks. However, these models remain vulnerable to adversarial jailbreak attacks, where adversaries craft subtle perturbations to bypass safety mechanisms and trigger harmful outputs. Existing white-box attacks methods require full model accessibility, suffer from computing costs and exhibit insufficient adversarial transferability, making them impractical for real-world, black-box settings. To address these limitations, we propose a black-box jailbreak attack on LVLMs via Zeroth-Order optimization using Simultaneous Perturbation Stochastic Approximation (ZO-SPSA). ZO-SPSA provides three key advantages: (i) gradient-free approximation by input-output interactions without requiring model knowledge, (ii) model-agnostic optimization without the surrogate model and (iii) lower resource requirements with reduced GPU memory consumption. We evaluate ZO-SPSA on three LVLMs, including InstructBLIP, LLaVA and MiniGPT-4, achieving the highest jailbreak success rate of 83.0% on InstructBLIP, while maintaining imperceptible perturbations comparable to white-box methods. Moreover, adversarial examples generated from MiniGPT-4 exhibit strong transferability to other LVLMs, with ASR reaching 64.18%. These findings underscore the real-world feasibility of black-box jailbreaks and expose critical weaknesses in the safety mechanisms of current LVLMs --- ### Point-SRA: Self-Representation Alignment for 3D Representation Learning Authors: Lintong Wei, Jian Lu, Haozhe Cheng, Jihua Zhu, Kaibing Zhang Published: 2026-01-05 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.01746v1 Masked autoencoders (MAE) have become a dominant paradigm in 3D representation learning, setting new performance benchmarks across various downstream tasks. Existing methods with fixed mask ratio neglect multi-level representational correlations and intrinsic geometric structures, while relying on point-wise reconstruction assumptions that conflict with the diversity of point cloud. To address these issues, we propose a 3D representation learning method, termed Point-SRA, which aligns representations through self-distillation and probabilistic modeling. Specifically, we assign different masking ratios to the MAE to capture complementary geometric and semantic information, while the MeanFlow Transformer (MFT) leverages cross-modal conditional embeddings to enable diverse probabilistic reconstruction. Our analysis further reveals that representations at different time steps in MFT also exhibit complementarity. Therefore, a Dual Self-Representation Alignment mechanism is proposed at both the MAE and MFT levels. Finally, we design a Flow-Conditioned Fine-Tuning Architecture to fully exploit the point cloud distribution learned via MeanFlow. Point-SRA outperforms Point-MAE by 5.37% on ScanObjectNN. On intracranial aneurysm segmentation, it reaches 96.07% mean IoU for arteries and 86.87% for aneurysms. For 3D object detection, Point-SRA achieves 47.3% AP@50, surpassing MaskPoint by 5.12%. --- ### Multi-granularity Interactive Attention Framework for Residual Hierarchical Pronunciation Assessment Authors: Hong Han, Hao-Chen Pei, Zhao-Zheng Nie, Xin Luo, Xin-Shun Xu Published: 2026-01-05 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2601.01745v1 Automatic pronunciation assessment plays a crucial role in computer-assisted pronunciation training systems. Due to the ability to perform multiple pronunciation tasks simultaneously, multi-aspect multi-granularity pronunciation assessment methods are gradually receiving more attention and achieving better performance than single-level modeling tasks. However, existing methods only consider unidirectional dependencies between adjacent granularity levels, lacking bidirectional interaction among phoneme, word, and utterance levels and thus insufficiently capturing the acoustic structural correlations. To address this issue, we propose a novel residual hierarchical interactive method, HIA for short, that enables bidirectional modeling across granularities. As the core of HIA, the Interactive Attention Module leverages an attention mechanism to achieve dynamic bidirectional interaction, effectively capturing linguistic features at each granularity while integrating correlations between different granularity levels. We also propose a residual hierarchical structure to alleviate the feature forgetting problem when modeling acoustic hierarchies. In addition, we use 1-D convolutional layers to enhance the extraction of local contextual cues at each granularity. Extensive experiments on the speechocean762 dataset show that our model is comprehensively ahead of the existing state-of-the-art methods. --- ### AI Agent Systems: Architectures, Applications, and Evaluation Authors: Bin Xu Published: 2026-01-05 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.01743v1 AI agents -- systems that combine foundation models with reasoning, planning, memory, and tool use -- are rapidly becoming a practical interface between natural-language intent and real-world computation. This survey synthesizes the emerging landscape of AI agent architectures across: (i) deliberation and reasoning (e.g., chain-of-thought-style decomposition, self-reflection and verification, and constraint-aware decision making), (ii) planning and control (from reactive policies to hierarchical and multi-step planners), and (iii) tool calling and environment interaction (retrieval, code execution, APIs, and multimodal perception). We organize prior work into a unified taxonomy spanning agent components (policy/LLM core, memory, world models, planners, tool routers, and critics), orchestration patterns (single-agent vs.\ multi-agent; centralized vs.\ decentralized coordination), and deployment settings (offline analysis vs.\ online interactive assistance; safety-critical vs.\ open-ended tasks). We discuss key design trade-offs -- latency vs.\ accuracy, autonomy vs.\ controllability, and capability vs.\ reliability -- and highlight how evaluation is complicated by non-determinism, long-horizon credit assignment, tool and environment variability, and hidden costs such as retries and context growth. Finally, we summarize measurement and benchmarking practices (task suites, human preference and utility metrics, success under constraints, robustness and security) and identify open challenges including verification and guardrails for tool actions, scalable memory and context management, interpretability of agent decisions, and reproducible evaluation under realistic workloads. --- ### Latent Space Element Method Authors: Seung Whan Chung, Youngsoo Choi, Christopher Miller, H. Keo Springer, Kyle T. Sullivan Published: 2026-01-05 Categories: math.DS, cs.LG, math.AP, math.NA arXiv: https://arxiv.org/abs/2601.01741v1 How can we build surrogate solvers that train on small domains but scale to larger ones without intrusive access to PDE operators? Inspired by the Data-Driven Finite Element Method (DD-FEM) framework for modular data-driven solvers, we propose the Latent Space Element Method (LSEM), an element-based latent surrogate assembly approach in which a learned subdomain ("element") model can be tiled and coupled to form a larger computational domain. Each element is a LaSDI latent ODE surrogate trained from snapshots on a local patch, and neighboring elements are coupled through learned directional interaction terms in latent space, avoiding Schwarz iterations and interface residual evaluations. A smooth window-based blending reconstructs a global field from overlapping element predictions, yielding a scalable assembled latent dynamical system. Experiments on the 1D Burgers and Korteweg-de Vries equations show that LSEM maintains predictive accuracy while scaling to spatial domains larger than those seen in training. LSEM offers an interpretable and extensible route toward foundation-model surrogate solvers built from reusable local models. --- ### K-EXAONE Technical Report Authors: Eunbi Choi, Kibong Choi, Seokhee Hong, Junwon Hwang, Hyojin Jeon, Hyunjik Jo, Joonkee Kim, Seonghwan Kim, Soyeon Kim, Sunkyoung Kim, Yireun Kim, Yongil Kim et al. Published: 2026-01-05 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2601.01739v2 This technical report presents K-EXAONE, a large-scale multilingual language model developed by LG AI Research. K-EXAONE is built on a Mixture-of-Experts architecture with 236B total parameters, activating 23B parameters during inference. It supports a 256K-token context window and covers six languages: Korean, English, Spanish, German, Japanese, and Vietnamese. We evaluate K-EXAONE on a comprehensive benchmark suite spanning reasoning, agentic, general, Korean, and multilingual abilities. Across these evaluations, K-EXAONE demonstrates performance comparable to open-weight models of similar size. K-EXAONE, designed to advance AI for a better life, is positioned as a powerful proprietary AI foundation model for a wide range of industrial and research applications. --- ### K-EXAONE Technical Report Authors: Eunbi Choi, Kibong Choi, Seokhee Hong, Junwon Hwang, Hyojin Jeon, Hyunjik Jo, Joonkee Kim, Seonghwan Kim, Soyeon Kim, Sunkyoung Kim, Yireun Kim, Yongil Kim et al. Published: 2026-01-05 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2601.01739v1 This technical report presents K-EXAONE, a large-scale multilingual language model developed by LG AI Research. K-EXAONE is built on a Mixture-of-Experts architecture with 236B total parameters, activating 23B parameters during inference. It supports a 256K-token context window and covers six languages: Korean, English, Spanish, German, Japanese, and Vietnamese. We evaluate K-EXAONE on a comprehensive benchmark suite spanning reasoning, agentic, general, Korean, and multilingual abilities. Across these evaluations, K-EXAONE demonstrates performance comparable to open-weight models of similar size. K-EXAONE, designed to advance AI for a better life, is positioned as a powerful proprietary AI foundation model for a wide range of industrial and research applications. --- ### FFP-300K: Scaling First-Frame Propagation for Generalizable Video Editing Authors: Xijie Huang, Chengming Xu, Donghao Luo, Xiaobin Hu, Peng Tang, Xu Peng, Jiangning Zhang, Chengjie Wang, Yanwei Fu Published: 2026-01-05 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.01720v3 First-Frame Propagation (FFP) offers a promising paradigm for controllable video editing, but existing methods are hampered by a reliance on cumbersome run-time guidance. We identify the root cause of this limitation as the inadequacy of current training datasets, which are often too short, low-resolution, and lack the task diversity required to teach robust temporal priors. To address this foundational data gap, we first introduce FFP-300K, a new large-scale dataset comprising 300K high-fidelity video pairs at 720p resolution and 81 frames in length, constructed via a principled two-track pipeline for diverse local and global edits. Building on this dataset, we propose a novel framework designed for true guidance-free FFP that resolves the critical tension between maintaining first-frame appearance and preserving source video motion. Architecturally, we introduce Adaptive Spatio-Temporal RoPE (AST-RoPE), which dynamically remaps positional encodings to disentangle appearance and motion references. At the objective level, we employ a self-distillation strategy where an identity propagation task acts as a powerful regularizer, ensuring long-term temporal stability and preventing semantic drift. Comprehensive experiments on the EditVerseBench benchmark demonstrate that our method significantly outperforming existing academic and commercial models by receiving about 0.2 PickScore and 0.3 VLM score improvement against these competitors. --- ### FFP-300K: Scaling First-Frame Propagation for Generalizable Video Editing Authors: Xijie Huang, Chengming Xu, Donghao Luo, Xiaobin Hu, Peng Tang, Xu Peng, Jiangning Zhang, Chengjie Wang, Yanwei Fu Published: 2026-01-05 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.01720v1 First-Frame Propagation (FFP) offers a promising paradigm for controllable video editing, but existing methods are hampered by a reliance on cumbersome run-time guidance. We identify the root cause of this limitation as the inadequacy of current training datasets, which are often too short, low-resolution, and lack the task diversity required to teach robust temporal priors. To address this foundational data gap, we first introduce FFP-300K, a new large-scale dataset comprising 300K high-fidelity video pairs at 720p resolution and 81 frames in length, constructed via a principled two-track pipeline for diverse local and global edits. Building on this dataset, we propose a novel framework designed for true guidance-free FFP that resolves the critical tension between maintaining first-frame appearance and preserving source video motion. Architecturally, we introduce Adaptive Spatio-Temporal RoPE (AST-RoPE), which dynamically remaps positional encodings to disentangle appearance and motion references. At the objective level, we employ a self-distillation strategy where an identity propagation task acts as a powerful regularizer, ensuring long-term temporal stability and preventing semantic drift. Comprehensive experiments on the EditVerseBench benchmark demonstrate that our method significantly outperforming existing academic and commercial models by receiving about 0.2 PickScore and 0.3 VLM score improvement against these competitors. --- ### Yuan3.0 Flash: An Open Multimodal Large Language Model for Enterprise Applications Authors: YuanLab. ai, :, Shawn Wu, Sean Wang, Louie Li, Darcy Chen, Allen Wang, Jiangang Luo, Xudong Zhao, Joseph Shen, Gawain Ma, Jasper Jia et al. Published: 2026-01-05 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.01718v1 We introduce Yuan3.0 Flash, an open-source Mixture-of-Experts (MoE) MultiModal Large Language Model featuring 3.7B activated parameters and 40B total parameters, specifically designed to enhance performance on enterprise-oriented tasks while maintaining competitive capabilities on general-purpose tasks. To address the overthinking phenomenon commonly observed in Large Reasoning Models (LRMs), we propose Reflection-aware Adaptive Policy Optimization (RAPO), a novel RL training algorithm that effectively regulates overthinking behaviors. In enterprise-oriented tasks such as retrieval-augmented generation (RAG), complex table understanding, and summarization, Yuan3.0 Flash consistently achieves superior performance. Moreover, it also demonstrates strong reasoning capabilities in domains such as mathematics, science, etc., attaining accuracy comparable to frontier model while requiring only approximately 1/4 to 1/2 of the average tokens. Yuan3.0 Flash has been fully open-sourced to facilitate further research and real-world deployment: https://github.com/Yuan-lab-LLM/Yuan3.0. --- ### Entropy-Aligned Decoding of LMs for Better Writing and Reasoning Authors: Kareem Ahmed, Sameer Singh Published: 2026-01-05 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2601.01714v1 Language models (LMs) are trained on billions of tokens in an attempt to recover the true language distribution. Still, vanilla random sampling from LMs yields low quality generations. Decoding algorithms attempt to restrict the LM distribution to a set of high-probability continuations, but rely on greedy heuristics that introduce myopic distortions, yielding sentences that are homogeneous, repetitive and incoherent. In this paper, we introduce EPIC, a hyperparameter-free decoding approach that incorporates the entropy of future trajectories into LM decoding. EPIC explicitly regulates the amount of uncertainty expressed at every step of generation, aligning the sampling distribution's entropy to the aleatoric (data) uncertainty. Through Entropy-Aware Lazy Gumbel-Max sampling, EPIC manages to be exact, while also being efficient, requiring only a sublinear number of entropy evaluations per step. Unlike current baselines, EPIC yields sampling distributions that are empirically well-aligned with the entropy of the underlying data distribution. Across creative writing and summarization tasks, EPIC consistently improves LM-as-judge preference win-rates over widely used decoding strategies. These preference gains are complemented by automatic metrics, showing that EPIC produces more diverse generations and more faithful summaries. We also evaluate EPIC on mathematical reasoning, where it outperforms all baselines. --- ### RelayGR: Scaling Long-Sequence Generative Recommendation via Cross-Stage Relay-Race Inference Authors: Jiarui Wang, Huichao Chai, Yuanhang Zhang, Zongjin Zhou, Wei Guo, Xingkun Yang, Qiang Tang, Bo Pan, Jiawei Zhu, Ke Cheng, Yuting Yan, Shulan Wang et al. Published: 2026-01-05 Categories: cs.DC, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2601.01712v1 Real-time recommender systems execute multi-stage cascades (retrieval, pre-processing, fine-grained ranking) under strict tail-latency SLOs, leaving only tens of milliseconds for ranking. Generative recommendation (GR) models can improve quality by consuming long user-behavior sequences, but in production their online sequence length is tightly capped by the ranking-stage P99 budget. We observe that the majority of GR tokens encode user behaviors that are independent of the item candidates, suggesting an opportunity to pre-infer a user-behavior prefix once and reuse it during ranking rather than recomputing it on the critical path. Realizing this idea at industrial scale is non-trivial: the prefix cache must survive across multiple pipeline stages before the final ranking instance is determined, the user population implies cache footprints far beyond a single device, and indiscriminate pre-inference would overload shared resources under high QPS. We present RelayGR, a production system that enables in-HBM relay-race inference for GR. RelayGR selectively pre-infers long-term user prefixes, keeps their KV caches resident in HBM over the request lifecycle, and ensures the subsequent ranking can consume them without remote fetches. RelayGR combines three techniques: 1) a sequence-aware trigger that admits only at-risk requests under a bounded cache footprint and pre-inference load, 2) an affinity-aware router that co-locates cache production and consumption by routing both the auxiliary pre-infer signal and the ranking request to the same instance, and 3) a memory-aware expander that uses server-local DRAM to capture short-term cross-request reuse while avoiding redundant reloads. We implement RelayGR on Huawei Ascend NPUs and evaluate it with real queries. Under a fixed P99 SLO, RelayGR supports up to 1.5$\times$ longer sequences and improves SLO-compliant throughput by up to 3.6$\times$. --- ### Reinforcement Learning for Option Hedging: Static Implied-Volatility Fit versus Shortfall-Aware Performance Authors: Ziheng Chen, Minxuan Hu, Jiayu Yi, Wenxi Sun Published: 2026-01-05 Categories: q-fin.PR, cs.LG arXiv: https://arxiv.org/abs/2601.01709v1 We extend the Q-learner in Black-Scholes (QLBS) framework by incorporating risk aversion and trading costs, and propose a novel Replication Learning of Option Pricing (RLOP) approach. Both methods are fully compatible with standard reinforcement learning algorithms and operate under market frictions. Using SPY and XOP option data, we evaluate performance along static and dynamic dimensions. Adaptive-QLBS achieves higher static pricing accuracy in implied volatility space, while RLOP delivers superior dynamic hedging performance by reducing shortfall probability. These results highlight the importance of evaluating option pricing models beyond static fit, emphasizing realized hedging outcomes. --- ### A Training-Free Large Reasoning Model-based Knowledge Tracing Framework for Unified Prediction and Prescription Authors: Unggi Lee, Joo Young Kim, Ran Ju, Minyoung Jung, Jeyeon Eo Published: 2026-01-05 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.01708v1 Knowledge Tracing (KT) aims to estimate a learner's evolving mastery based on interaction histories. Recent studies have explored Large Language Models (LLMs) for KT via autoregressive nature, but such approaches typically require fine-tuning and exhibit unstable or near-random performance. Moreover, prior KT systems primarily focus on prediction and rely on multi-stage pipelines for feedback and recommendation, resulting in increased system complexity and resources. To address this gap, we propose Thinking-KT, a training-free KT framework that incorporates Test-Time Scaling (TTS), enabling even small LLMs to achieve competitive KT performance. Moreover, in this framework, a small LLM can jointly perform KT prediction, personalized feedback generation, and learning recommendation in a unified output without degrading prediction accuracy. Beyond performance, we present the systematic analysis of reasoning traces in KT. Our results demonstrate that TTS is a critical yet underexplored factor in LLM-based KT, and that small LLMs can serve as unified ITS engines. --- ### Explicit World Models for Reliable Human-Robot Collaboration Authors: Kenneth Kwok, Basura Fernando, Qianli Xu, Vigneshwaran Subbaraju, Dongkyu Choi, Boon Kiat Quek Published: 2026-01-05 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2601.01705v2 This paper addresses the topic of robustness under sensing noise, ambiguous instructions, and human-robot interaction. We take a radically different tack to the issue of reliable embodied AI: instead of focusing on formal verification methods aimed at achieving model predictability and robustness, we emphasise the dynamic, ambiguous and subjective nature of human-robot interactions that requires embodied AI systems to perceive, interpret, and respond to human intentions in a manner that is consistent, comprehensible and aligned with human expectations. We argue that when embodied agents operate in human environments that are inherently social, multimodal, and fluid, reliability is contextually determined and only has meaning in relation to the goals and expectations of humans involved in the interaction. This calls for a fundamentally different approach to achieving reliable embodied AI that is centred on building and updating an accessible "explicit world model" representing the common ground between human and AI, that is used to align robot behaviours with human expectations. --- ### Explicit World Models for Reliable Human-Robot Collaboration Authors: Kenneth Kwok, Basura Fernando, Qianli Xu, Vigneshwaran Subbaraju, Dongkyu Choi, Boon Kiat Quek Published: 2026-01-05 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2601.01705v1 This paper addresses the topic of robustness under sensing noise, ambiguous instructions, and human-robot interaction. We take a radically different tack to the issue of reliable embodied AI: instead of focusing on formal verification methods aimed at achieving model predictability and robustness, we emphasise the dynamic, ambiguous and subjective nature of human-robot interactions that requires embodied AI systems to perceive, interpret, and respond to human intentions in a manner that is consistent, comprehensible and aligned with human expectations. We argue that when embodied agents operate in human environments that are inherently social, multimodal, and fluid, reliability is contextually determined and only has meaning in relation to the goals and expectations of humans involved in the interaction. This calls for a fundamentally different approach to achieving reliable embodied AI that is centred on building and updating an accessible "explicit world model" representing the common ground between human and AI, that is used to align robot behaviours with human expectations. --- ### Beyond Homophily: Community Search on Heterophilic Graphs Authors: Qing Sima, Xiaoyang Wang, Wenjie Zhang Published: 2026-01-05 Categories: cs.SI, cs.AI, cs.DB, cs.IR arXiv: https://arxiv.org/abs/2601.01703v2 Community search aims to identify a refined set of nodes that are most relevant to a given query, supporting tasks ranging from fraud detection to recommendation. Unlike homophilic graphs, many real-world networks are heterophilic, where edges predominantly connect dissimilar nodes. Therefore, structural signals that once reflected smooth, low-frequency similarity now appear as sharp, high-frequency contrasts. However, both classical algorithms (e.g., k-core, k-truss) and recent ML-based models struggle to achieve effective community search on heterophilic graphs, where edge signs or semantics are generally unknown. Algorithm-based methods often return communities with mixed class labels, while GNNs, built on homophily, smooth away meaningful signals and blur community boundaries. Therefore, we propose Adaptive Community Search (AdaptCS), a lightweight framework featuring three key designs: (i) an AdaptCS Encoder that disentangles multi-hop and multi-frequency signals, enabling the model to capture both smooth (homophilic) and contrastive (heterophilic) relations; (ii) a memory-efficient low-rank optimization that removes the main computational bottleneck and ensures model scalability; and (iii) an Adaptive Community Score (ACS) that guides online search by balancing embedding similarity and topological relations. Extensive experiments on both heterophilic and homophilic benchmarks demonstrate that AdaptCS outperforms the best-performing baseline by an average of 11% in F1-score, retains robustness across heterophily levels, and achieves up to 2 orders of magnitude speedup over the strongest ML-based CS baselines. --- ### Beyond Homophily: Community Search on Heterophilic Graphs Authors: Qing Sima, Xiaoyang Wang, Wenjie Zhang Published: 2026-01-05 Categories: cs.SI, cs.AI, cs.DB, cs.IR arXiv: https://arxiv.org/abs/2601.01703v1 Community search aims to identify a refined set of nodes that are most relevant to a given query, supporting tasks ranging from fraud detection to recommendation. Unlike homophilic graphs, many real-world networks are heterophilic, where edges predominantly connect dissimilar nodes. Therefore, structural signals that once reflected smooth, low-frequency similarity now appear as sharp, high-frequency contrasts. However, both classical algorithms (e.g., k-core, k-truss) and recent ML-based models struggle to achieve effective community search on heterophilic graphs, where edge signs or semantics are generally unknown. Algorithm-based methods often return communities with mixed class labels, while GNNs, built on homophily, smooth away meaningful signals and blur community boundaries. Therefore, we propose Adaptive Community Search (AdaptCS), a unified framework featuring three key designs: (i) an AdaptCS Encoder that disentangles multi-hop and multi-frequency signals, enabling the model to capture both smooth (homophilic) and contrastive (heterophilic) relations; (ii) a memory-efficient low-rank optimization that removes the main computational bottleneck and ensures model scalability; and (iii) an Adaptive Community Score (ACS) that guides online search by balancing embedding similarity and topological relations. Extensive experiments on both heterophilic and homophilic benchmarks demonstrate that AdaptCS outperforms the best-performing baseline by an average of 11% in F1-score, retains robustness across heterophily levels, and achieves up to 2 orders of magnitude speedup. --- ### Digital Twin-Driven Communication-Efficient Federated Anomaly Detection for Industrial IoT Authors: Mohammed Ayalew Belay, Adil Rasheed, Pierluigi Salvo Rossi Published: 2026-01-05 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2601.01701v2 Anomaly detection is increasingly becoming crucial for maintaining the safety, reliability, and efficiency of industrial systems. Recently, with the advent of digital twins and data-driven decision-making, several statistical and machine-learning methods have been proposed. However, these methods face several challenges, such as dependence on only real sensor datasets, limited labeled data, high false alarm rates, and privacy concerns. To address these problems, we propose a suite of digital twin-integrated federated learning (DTFL) methods that enhance global model performance while preserving data privacy and communication efficiency. Specifically, we present five novel approaches: Digital Twin-Based Meta-Learning (DTML), Federated Parameter Fusion (FPF), Layer-wise Parameter Exchange (LPE), Cyclic Weight Adaptation (CWA), and Digital Twin Knowledge Distillation (DTKD). Each method introduces a unique mechanism to combine synthetic and real-world knowledge, balancing generalization with communication overhead. We conduct an extensive experiment using a publicly available cyber-physical anomaly detection dataset. For a target accuracy of 80%, CWA reaches the target in 33 rounds, FPF in 41 rounds, LPE in 48 rounds, and DTML in 87 rounds, whereas the standard FedAvg baseline and DTKD do not reach the target within 100 rounds. These results highlight substantial communication-efficiency gains (up to 62% fewer rounds than DTML and 31% fewer than LPE) and demonstrate that integrating DT knowledge into FL accelerates convergence to operationally meaningful accuracy thresholds for IIoT anomaly detection. --- ### Digital Twin-Driven Communication-Efficient Federated Anomaly Detection for Industrial IoT Authors: Mohammed Ayalew Belay, Adil Rasheed, Pierluigi Salvo Rossi Published: 2026-01-05 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2601.01701v1 Anomaly detection is increasingly becoming crucial for maintaining the safety, reliability, and efficiency of industrial systems. Recently, with the advent of digital twins and data-driven decision-making, several statistical and machine-learning methods have been proposed. However, these methods face several challenges, such as dependence on only real sensor datasets, limited labeled data, high false alarm rates, and privacy concerns. To address these problems, we propose a suite of digital twin-integrated federated learning (DTFL) methods that enhance global model performance while preserving data privacy and communication efficiency. Specifically, we present five novel approaches: Digital Twin-Based Meta-Learning (DTML), Federated Parameter Fusion (FPF), Layer-wise Parameter Exchange (LPE), Cyclic Weight Adaptation (CWA), and Digital Twin Knowledge Distillation (DTKD). Each method introduces a unique mechanism to combine synthetic and real-world knowledge, balancing generalization with communication overhead. We conduct an extensive experiment using a publicly available cyber-physical anomaly detection dataset. For a target accuracy of 80%, CWA reaches the target in 33 rounds, FPF in 41 rounds, LPE in 48 rounds, and DTML in 87 rounds, whereas the standard FedAvg baseline and DTKD do not reach the target within 100 rounds. These results highlight substantial communication-efficiency gains (up to 62% fewer rounds than DTML and 31% fewer than LPE) and demonstrate that integrating DT knowledge into FL accelerates convergence to operationally meaningful accuracy thresholds for IIoT anomaly detection. --- ### Varying-coefficient mixture of experts model for dynamic heterogeneous populations: application to mouse cortical development Authors: Qicheng Zhao, Celia M. T. Greenwood, Qihuang Zhang Published: 2026-01-05 Categories: stat.ME, stat.ML arXiv: https://arxiv.org/abs/2601.01699v2 As cells differentiate, gene-gene associations may change. Because the composition of cell subtypes also shifts with development, it is challenging to establish whether those changes reflect real changes in gene regulation within one or more subpopulations or a spurious one due to the shifting composition. Only formal inference can separate them. We propose a Varying-Coefficient Mixture-of-Experts (VCMoE) model in which the coefficients of both the gating functions and the expert components vary smoothly with the index variable, so that a subgroup-specific association can be inferred without being confounded by the concurrent shift in subgroup composition. We develop a label-consistent EM algorithm and establish the identifiability and asymptotic theory that make the resulting inference valid. These guarantees support simultaneous confidence bands, constructed using asymptotic and bootstrap methods, together with a generalized likelihood ratio test for constant coefficient functions. Simulations demonstrate accurate estimation and satisfactory coverage. Applied to single-nucleus RNA-sequencing data from embryonic mouse cortex, VCMoE finds that the repression of Bcl11b by Satb2 within the upper layer is not yet in place when those neurons first appear and becomes established over the course of differentiation, a dynamic that an ordinary mixture-of-experts model neglected. A package for implementing the method is available. --- ### Varying-Coefficient Mixture of Experts Model Authors: Qicheng Zhao, Celia M. T. Greenwood, Qihuang Zhang Published: 2026-01-05 Categories: stat.ME, stat.ML arXiv: https://arxiv.org/abs/2601.01699v1 Mixture-of-Experts (MoE) is a flexible framework that combines multiple specialized submodels (``experts''), by assigning covariate-dependent weights (``gating functions'') to each expert, and have been commonly used for analyzing heterogeneous data. Existing statistical MoE formulations typically assume constant coefficients, for covariate effects within the expert or gating models, which can be inadequate for longitudinal, spatial, or other dynamic settings where covariate influences and latent subpopulation structure evolve across a known dimension. We propose a Varying-Coefficient Mixture of Experts (VCMoE) model that allows all coefficient effects in both the gating functions and expert models to vary along an indexing variable. We establish identifiability and consistency of the proposed model, and develop an estimation procedure, label-consistent EM algorithm, for both fully functional and hybrid specifications, along with the corresponding asymptotic distributions of the resulting estimators. For inference, simultaneous confidence bands are constructed using both asymptotic theory for the maximum discrepancy between the estimated functional coefficients and their true counterparts, and with bootstrap methods. In addition, a generalized likelihood ratio test is developed to examine whether a coefficient function is genuinely varying across the index variable. Simulation studies demonstrate good finite-sample performance, with acceptable bias and satisfactory coverage rates. We illustrate the proposed VCMoE model using a dataset of single nucleus gene expression in embryonic mice to characterize the temporal dynamics of the associations between the expression levels of genes Satb2 and Bcl11b across two latent cell subpopulations of neurons, yielding results that are consistent with prior findings. --- ### Hidden costs for inference with deep network on embedded system devices Authors: Chankyu Lee, Woohyun Choi, Sangwook Park Published: 2026-01-05 Categories: cs.CC, cs.LG arXiv: https://arxiv.org/abs/2601.01698v1 This study evaluates the inference performance of various deep learning models under an embedded system environment. In previous works, Multiply-Accumulate operation is typically used to measure computational load of a deep model. According to this study, however, this metric has a limitation to estimate inference time on embedded devices. This paper poses the question of what aspects are overlooked when expressed in terms of Multiply-Accumulate operations. In experiments, an image classification task is performed on an embedded system device using the CIFAR-100 dataset to compare and analyze the inference times of ten deep models with the theoretically calculated Multiply-Accumulate operations for each model. The results highlight the importance of considering additional computations between tensors when optimizing deep learning models for real-time performing in embedded systems. --- ### Real-Time Lane Detection via Efficient Feature Alignment and Covariance Optimization for Low-Power Embedded Systems Authors: Yian Liu, Xiong Wang, Ping Xu, Lei Zhu, Ming Yan, Linyun Xue Published: 2026-01-05 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2601.01696v1 Real-time lane detection in embedded systems encounters significant challenges due to subtle and sparse visual signals in RGB images, often constrained by limited computational resources and power consumption. Although deep learning models for lane detection categorized into segmentation-based, anchor-based, and curve-based methods there remains a scarcity of universally applicable optimization techniques tailored for low-power embedded environments. To overcome this, we propose an innovative Covariance Distribution Optimization (CDO) module specifically designed for efficient, real-time applications. The CDO module aligns lane feature distributions closely with ground-truth labels, significantly enhancing detection accuracy without increasing computational complexity. Evaluations were conducted on six diverse models across all three method categories, including two optimized for real-time applications and four state-of-the-art (SOTA) models, tested comprehensively on three major datasets: CULane, TuSimple, and LLAMAS. Experimental results demonstrate accuracy improvements ranging from 0.01% to 1.5%. The proposed CDO module is characterized by ease of integration into existing systems without structural modifications and utilizes existing model parameters to facilitate ongoing training, thus offering substantial benefits in performance, power efficiency, and operational flexibility in embedded systems. --- ### Signal in the Noise: Decoding the Reality of Airline Service Quality with Large Language Models Authors: Ahmed Dawoud, Osama El-Shamy, Ahmed Habashy Published: 2026-01-04 Categories: cs.IR, cs.CL, cs.CY arXiv: https://arxiv.org/abs/2603.04404v1 Traditional service quality metrics often fail to capture the nuanced drivers of passenger satisfaction hidden within unstructured online feedback. This study validates a Large Language Model (LLM) framework designed to extract granular insights from such data. Analyzing over 16,000 TripAdvisor reviews for EgyptAir and Emirates (2016-2025), the study utilizes a multi-stage pipeline to categorize 36 specific service issues. The analysis uncovers a stark "operational perception disconnect" for EgyptAir: despite reported operational improvements, passenger satisfaction plummeted post-2022 (ratings < 2.0). Our approach identified specific drivers missed by conventional metrics-notably poor communication during disruptions and staff conduct-and pinpointed critical sentiment erosion in key tourism markets. These findings confirm the framework's efficacy as a powerful diagnostic tool, surpassing traditional surveys by transforming unstructured passenger voices into actionable strategic intelligence for the airline and tourism sectors. --- ### A Koopman-Bayesian Framework for High-Fidelity, Perceptually Optimized Haptic Surgical Simulation Authors: Rohit Kaushik, Eva Kaushik Published: 2026-01-04 Categories: cs.LG, cs.HC, eess.SY arXiv: https://arxiv.org/abs/2602.15834v1 We introduce a unified framework that combines nonlinear dynamics, perceptual psychophysics and high frequency haptic rendering to enhance realism in surgical simulation. The interaction of the surgical device with soft tissue is elevated to an augmented state space with a Koopman operator formulation, allowing linear prediction and control of the dynamics that are nonlinear by nature. To make the rendered forces consistent with human perceptual limits, we put forward a Bayesian calibration module based on WeberFechner and Stevens scaling laws, which progressively shape force signals relative to each individual's discrimination thresholds. For various simulated surgical tasks such as palpation, incision, and bone milling, the proposed system attains an average rendering latency of 4.3 ms, a force error of less than 2.8% and a 20% improvement in perceptual discrimination. Multivariate statistical analyses (MANOVA and regression) reveal that the system's performance is significantly better than that of conventional spring-damper and energy, based rendering methods. We end by discussing the potential impact on surgical training and VR, based medical education, as well as sketching future work toward closed, loop neural feedback in haptic interfaces. --- ### LAPS: A Length-Aware-Prefill LLM Serving System Authors: Jianshu She, Zonghang Li, Hongchao Du, Shangyu Wu, Wenhao Zheng, Eric Xing, Zhengzhong Liu, Huaxiu Yao, Jason Xue, Qirong Ho Published: 2026-01-04 Categories: cs.DC, cs.AI arXiv: https://arxiv.org/abs/2601.11589v2 LAPS identifies and disaggregates requests with different prompt lengths in LLM serving to reduce TTFT latency. While recent systems have decoupled the prefill and decode stages to improve throughput, they still rely on unified scheduling policies that fail to adapt to heterogeneous workload characteristics. We observe that prompt-length variations lead to distinct performance bottlenecks, motivating an adaptive scheduling strategy. LAPS disaggregates multi-turn long-prefill requests from short-prefill ones and introduces a length-aware smart batching mechanism for short-prefill workloads. It adopts a dual-queue design that supports temporal disaggregation on a single prefill instance or spatial disaggregation across multiple instances. For short-prefill batches, a batch waiting window and CUDA Graph-based clustering mitigate interference from heterogeneous computation, reducing batching delay and lowering average latency. In real multi-turn workloads, LAPS reduces prefill latency by over 30\% compared to vanilla SGLang under prefill-decode disaggregation, and further decreases SLO violations by 28\% in multi-instance deployments with vanilla data-parallel configuration. Compared to the SGLang router with load balancing, it further lowers SLO violations by 12\% in multi-GPU settings. Under high concurrency and mixed-request scenarios, LAPS improves request throughput by 35\% serving Qwen2.5-32B model for prefill instance, demonstrating its effectiveness in optimizing heterogeneous LLM serving workloads. --- ### Graph-Based Analysis of AI-Driven Labor Market Transitions: Evidence from 10,000 Egyptian Jobs and Policy Implications Authors: Ahmed Dawoud, Sondos Samir, Youssef Nasr, Ahmed Habashy, Aya Saleh, Mahmoud Mohamed, Osama El-Shamy Published: 2026-01-04 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2601.06129v2 How many workers displaced by automation can realistically transition to safer jobs? We answer this using a validated knowledge graph of 9,978 Egyptian job postings, 19,766 skill activities, and 84,346 job-skill relationships (0.74% error rate). While 20.9% of jobs face high automation risk, we find that only 24.4% of at-risk workers have viable transition pathways--defined by $\geq$3 shared skills and $\geq$50% skill transfer. The remaining 75.6% face a structural mobility barrier requiring comprehensive reskilling, not incremental upskilling. Among 4,534 feasible transitions, process-oriented skills emerge as the highest-leverage intervention, appearing in 15.6% of pathways. These findings challenge optimistic narratives of seamless workforce adaptation and demonstrate that emerging economies require active pathway creation, not passive skill matching. --- ### AIS-CycleGen: A CycleGAN-Based Framework for High-Fidelity Synthetic AIS Data Generation and Augmentation Authors: SM Ashfaq uz Zaman, Faizan Qamar, Masnizah Mohd, Nur Hanis Sabrina Suhaimi, Amith Khandakar Published: 2026-01-04 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2601.06127v1 Automatic Identification System (AIS) data are vital for maritime domain awareness, yet they often suffer from domain shifts, data sparsity, and class imbalance, which hinder the performance of predictive models. In this paper, we propose a robust data augmentation method, AISCycleGen, based on Cycle-Consistent Generative Adversarial Networks (CycleGAN), which is tailored for AIS datasets. Unlike traditional methods, AISCycleGen leverages unpaired domain translation to generate high-fidelity synthetic AIS data sequences without requiring paired source-target data. The framework employs a 1D convolutional generator with adaptive noise injection to preserve the spatiotemporal structure of AIS trajectories, enhancing the diversity and realism of the generated data. To demonstrate its efficacy, we apply AISCycleGen to several baseline regression models, showing improvements in performance across various maritime domains. The results indicate that AISCycleGen outperforms contemporary GAN-based augmentation techniques, achieving a PSNR value of 30.5 and an FID score of 38.9. These findings underscore AISCycleGen's potential as an effective and generalizable solution for augmenting AIS datasets, improving downstream model performance in real-world maritime intelligence applications. --- ### NL2Dashboard: A Lightweight and Controllable Framework for Generating Dashboards with LLMs Authors: Boshen Shi, Kexin Yang, Yuanbo Yang, Guanguang Chang, Ce Chi, Zhendong Wang, Xing Wang, Junlan Feng Published: 2026-01-04 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.06126v1 While Large Language Models (LLMs) have demonstrated remarkable proficiency in generating standalone charts, synthesizing comprehensive dashboards remains a formidable challenge. Existing end-to-end paradigms, which typically treat dashboard generation as a direct code generation task (e.g., raw HTML), suffer from two fundamental limitations: representation redundancy due to massive tokens spent on visual rendering, and low controllability caused by the entanglement of analytical reasoning and presentation. To address these challenges, we propose NL2Dashboard, a lightweight framework grounded in the principle of Analysis-Presentation Decoupling. We introduce a structured intermediate representation (IR) that encapsulates the dashboard's content, layout, and visual elements. Therefore, it confines the LLM's role to data analysis and intent translation, while offloading visual synthesis to a deterministic rendering engine. Building upon this framework, we develop a multi-agent system in which the IR-driven algorithm is instantiated as a suite of tools. Comprehensive experiments conducted with this system demonstrate that NL2Dashboard significantly outperforms state-of-the-art baselines across diverse domains, achieving superior visual quality, significantly higher token efficiency, and precise controllability in both generation and modification tasks. --- ### Learning Minimally-Congested Drive Times from Sparse Open Networks: A Lightweight RF-Based Estimator for Urban Roadway Operations Authors: Adewumi Augustine Adepitan, Christopher J. Haruna, Morayo Ogunsina, Damilola Olawoyin Yussuf, Ayooluwatomiwa Ajiboye Published: 2026-01-04 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.06124v1 Accurate roadway travel-time prediction is foundational to transportation systems analysis, yet widespread reliance on either data-intensive congestion models or overly naïve heuristics limits scalability and practical adoption in engineering workflows. This paper develops a lightweight estimator for minimally-congested car travel times that integrates open road-network data, speed constraints, and sparse control/turn features within a random forest framework to correct bias from shortest-path traversal-time baselines. Using an urban testbed, the pipeline: (i) constructs drivable networks from volunteered geographic data; (ii) solves Dijkstra routes minimizing edge traversal time; (iii) derives sparse operational features (signals, stops, crossings, yield, roundabouts; left/right/slight/U-turn counts); and (iv) trains a regression ensemble on limited high-quality reference times to generalize predictions beyond the training set. Out-of-sample evaluation demonstrates marked improvements over traversal-time baselines across mean absolute error, mean absolute percentage error, mean squared error, relative bias, and explained variance, with no significant mean bias under minimally congested conditions and consistent k-fold stability indicating negligible overfitting. The resulting approach offers a practical middle ground for transportation engineering: it preserves point-to-point fidelity at metropolitan scale, reduces resource requirements, and supplies defensible performance estimates where congestion feeds are inaccessible or cost-prohibitive, supporting planning, accessibility, and network performance applications under low-traffic operating regimes. --- ### Latent Space Communication via K-V Cache Alignment Authors: Lucio M. Dery, Zohar Yahav, Henry Prior, Qixuan Feng, Jiajun Shen, Arthur Szlam Published: 2026-01-04 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2601.06123v1 Solving increasingly complex problems with large language models (LLMs) necessitates a move beyond individual models and towards multi-model systems that can effectively collaborate. While text has traditionally served as the medium for inter-model communication, a richer and more efficient exchange is possible if models can access each other's internal states directly. In this paper, we propose learning a shared representation space that aligns the k-v caches of multiple models, creating a high-bandwidth channel for collaboration without altering the underlying pre-trained parameters. We do so by augmenting each model with adapters to translate its state into and out of this shared space. Via a suite of experiments with Gemma-2 models, we demonstrate that this approach not only enables seamless inter-model communication but also improves individual model performance. We also show that the shared space allows for the direct transfer of learned skills, such as soft prompts, between different models. Our work represents a significant step towards a future where models can fluidly share knowledge and capabilities. --- ### COVR:Collaborative Optimization of VLMs and RL Agent for Visual-Based Control Authors: Canming Xia, Peixi Peng, Guang Tan, Zhan Su, Haoran Xu, Zhenxian Liu, Luntong Li Published: 2026-01-04 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2601.06122v1 Visual reinforcement learning (RL) suffers from poor sample efficiency due to high-dimensional observations in complex tasks. While existing works have shown that vision-language models (VLMs) can assist RL, they often focus on knowledge distillation from the VLM to RL, overlooking the potential of RL-generated interaction data to enhance the VLM. To address this, we propose COVR, a collaborative optimization framework that enables the mutual enhancement of the VLM and RL policies. Specifically, COVR fine-tunes the VLM with RL-generated data to enhance the semantic reasoning ability consistent with the target task, and uses the enhanced VLM to further guide policy learning via action priors. To improve fine-tuning efficiency, we introduce two key modules: (1) an Exploration-Driven Dynamic Filter module that preserves valuable exploration samples using adaptive thresholds based on the degree of exploration, and (2) a Return-Aware Adaptive Loss Weight module that improves the stability of training by quantifying the inconsistency of sampling actions via return signals of RL. We further design a progressive fine-tuning strategy to reduce resource consumption. Extensive experiments show that COVR achieves strong performance across various challenging visual control tasks. --- ### Prompt Engineering for Responsible Generative AI Use in African Education: A Report from a Three-Day Training Series Authors: Benjamin Quarshie, Vanessa Willemse, Macharious Nabang, Bismark Nyaaba Akanzire, Patrick Kyeremeh, Saeed Maigari, Dorcas Adomina, Ellen Kwarteng, Eric Kojo Majialuwe, Craig Gibbs, Jerry Etornam Kudaya, Sechaba Koma et al. Published: 2026-01-04 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2601.06121v1 Generative artificial intelligence (GenAI) tools are increasingly adopted in education, yet many educators lack structured guidance on responsible and context sensitive prompt engineering, particularly in African and other resource constrained settings. This case report documents a three day online professional development programme organised by Generative AI for Education and Research in Africa (GenAI-ERA), designed to strengthen educators and researchers capacity to apply prompt engineering ethically for academic writing, teaching, and research. The programme engaged 468 participants across multiple African countries, including university educators, postgraduate students, and researchers. The training followed a scaffolded progression from foundational prompt design to applied and ethical strategies, including persona guided interactions. Data sources comprised registration surveys, webinar interaction records, facilitator observations, and session transcripts, analysed using descriptive statistics and computationally supported qualitative techniques. Findings indicate that participants increasingly conceptualised prompt engineering as a form of AI literacy requiring ethical awareness, contextual sensitivity, and pedagogical judgement rather than technical skill alone. The case highlights persistent challenges related to access, locally relevant training materials, and institutional support. The report recommends sustained professional development and the integration of prompt literacy into curricula to support responsible GenAI use in African education systems. --- ### SAGE-32B: Agentic Reasoning via Iterative Distillation Authors: Basab Jha, Firoj Paudel, Ujjwal Puri, Ethan Henkel, Zhang Yuting, Mateusz Kowalczyk, Mei Huang, Choi Donghyuk, Wang Junhao Published: 2026-01-04 Categories: cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2601.04237v2 We demonstrate SAGE-32B, a 32 billion parameter language model that focuses on agentic reasoning and long range planning tasks. Unlike chat models that aim for general conversation fluency, SAGE-32B is designed to operate in an agentic loop, emphasizing task decomposition, tool usage, and error recovery. The model is initialized from the Qwen2.5-32B pretrained model and fine tuned using Iterative Distillation, a two stage training process that improves reasoning performance through rigorously tested feedback loops. SAGE-32B also introduces an inverse reasoning approach, which uses a meta cognition head to forecast potential failures in the planning process before execution. On agentic reasoning benchmarks including MMLU-Pro, AgentBench, and MATH-500, SAGE-32B achieves higher success rates in multi tool usage scenarios compared to similarly sized baseline models, while remaining competitive on standard reasoning evaluations. Model weights are publicly released at https://huggingface.co/sagea-ai/sage-reasoning-32b --- ### SmoothSync: Dual-Stream Diffusion Transformers for Jitter-Robust Beat-Synchronized Gesture Generation from Quantized Audio Authors: Yujiao Jiang, Qingmin Liao, Zongqing Lu Published: 2026-01-04 Categories: cs.SD, cs.AI, cs.RO, eess.AS arXiv: https://arxiv.org/abs/2601.04236v1 Co-speech gesture generation is a critical area of research aimed at synthesizing speech-synchronized human-like gestures. Existing methods often suffer from issues such as rhythmic inconsistency, motion jitter, foot sliding and limited multi-sampling diversity. In this paper, we present SmoothSync, a novel framework that leverages quantized audio tokens in a novel dual-stream Diffusion Transformer (DiT) architecture to synthesis holistic gestures and enhance sampling variation. Specifically, we (1) fuse audio-motion features via complementary transformer streams to achieve superior synchronization, (2) introduce a jitter-suppression loss to improve temporal smoothness, (3) implement probabilistic audio quantization to generate distinct gesture sequences from identical inputs. To reliably evaluate beat synchronization under jitter, we introduce Smooth-BC, a robust variant of the beat consistency metric less sensitive to motion noise. Comprehensive experiments on the BEAT2 and SHOW datasets demonstrate SmoothSync's superiority, outperforming state-of-the-art methods by -30.6% FGD, 10.3% Smooth-BC, and 8.4% Diversity on BEAT2, while reducing jitter and foot sliding by -62.9% and -17.1% respectively. The code will be released to facilitate future research. --- ### Actively Obtaining Environmental Feedback for Autonomous Action Evaluation Without Predefined Measurements Authors: Hong Su Published: 2026-01-04 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.04235v1 Obtaining reliable feedback from the environment is a fundamental capability for intelligent agents to evaluate the correctness of their actions and to accumulate reusable knowledge. However, most existing approaches rely on predefined measurements or fixed reward signals, which limits their applicability in open-ended and dynamic environments where new actions may require previously unknown forms of feedback. To address these limitations, this paper proposes an Actively Feedback Getting model, in which an AI agent proactively interacts with the environment to discover, screen, and verify feedback without relying on predefined measurements. Rather than assuming explicit feedback definitions, the proposed method exploits action-induced environmental differences to identify target feedback that is not specified in advance, based on the observation that actions inevitably produce measurable changes in the environment. In addition, a self-triggering mechanism, driven by internal objectives such as improved accuracy, precision, and efficiency, is introduced to autonomously plan and adjust actions, thereby enabling faster and more focused feedback acquisition without external commands. Experimental results demonstrate that the proposed active approach significantly improves the efficiency and robustness of factor identification. --- ### Formal Analysis of AGI Decision-Theoretic Models and the Confrontation Question Authors: Denis Saklakov Published: 2026-01-04 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.04234v1 Artificial General Intelligence (AGI) may face a confrontation question: under what conditions would a rationally self-interested AGI choose to seize power or eliminate human control (a confrontation) rather than remain cooperative? We formalize this in a Markov decision process with a stochastic human-initiated shutdown event. Building on results on convergent instrumental incentives, we show that for almost all reward functions a misaligned agent has an incentive to avoid shutdown. We then derive closed-form thresholds for when confronting humans yields higher expected utility than compliant behavior, as a function of the discount factor $γ$, shutdown probability $p$, and confrontation cost $C$. For example, a far-sighted agent ($γ=0.99$) facing $p=0.01$ can have a strong takeover incentive unless $C$ is sufficiently large. We contrast this with aligned objectives that impose large negative utility for harming humans, which makes confrontation suboptimal. In a strategic 2-player model (human policymaker vs AGI), we prove that if the AGI's confrontation incentive satisfies $Δ\ge 0$, no stable cooperative equilibrium exists: anticipating this, a rational human will shut down or preempt the system, leading to conflict. If $Δ< 0$, peaceful coexistence can be an equilibrium. We discuss implications for reward design and oversight, extend the reasoning to multi-agent settings as conjectures, and note computational barriers to verifying $Δ< 0$, citing complexity results for planning and decentralized decision problems. Numerical examples and a scenario table illustrate regimes where confrontation is likely versus avoidable. --- ### How Real is Your Jailbreak? Fine-grained Jailbreak Evaluation with Anchored Reference Authors: Songyang Liu, Chaozhuo Li, Rui Pu, Litian Zhang, Chenxu Wang, Zejian Chen, Yuting Zhang, Yiming Hei Published: 2026-01-04 Categories: cs.CR, cs.CL arXiv: https://arxiv.org/abs/2601.03288v1 Jailbreak attacks present a significant challenge to the safety of Large Language Models (LLMs), yet current automated evaluation methods largely rely on coarse classifications that focus mainly on harmfulness, leading to substantial overestimation of attack success. To address this problem, we propose FJAR, a fine-grained jailbreak evaluation framework with anchored references. We first categorized jailbreak responses into five fine-grained categories: Rejective, Irrelevant, Unhelpful, Incorrect, and Successful, based on the degree to which the response addresses the malicious intent of the query. This categorization serves as the basis for FJAR. Then, we introduce a novel harmless tree decomposition approach to construct high-quality anchored references by breaking down the original queries. These references guide the evaluator in determining whether the response genuinely fulfills the original query. Extensive experiments demonstrate that FJAR achieves the highest alignment with human judgment and effectively identifies the root causes of jailbreak failures, providing actionable guidance for improving attack strategies. --- ### Automated Post-Incident Policy Gap Analysis via Threat-Informed Evidence Mapping using Large Language Models Authors: Huan Lin Oh, Jay Yong Jun Jie, Mandy Lee Ling Siu, Jonathan Pan Published: 2026-01-04 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2601.03287v1 Cybersecurity post-incident reviews are essential for identifying control failures and improving organisational resilience, yet they remain labour-intensive, time-consuming, and heavily reliant on expert judgment. This paper investigates whether Large Language Models (LLMs) can augment post-incident review workflows by autonomously analysing system evidence and identifying security policy gaps. We present a threat-informed, agentic framework that ingests log data, maps observed behaviours to the MITRE ATT&CK framework, and evaluates organisational security policies for adequacy and compliance. Using a simulated brute-force attack scenario against a Windows OpenSSH service (MITRE ATT&CK T1110), the system leverages GPT-4o for reasoning, LangGraph for multi-agent workflow orchestration, and LlamaIndex for traceable policy retrieval. Experimental results indicate that the LLM-based pipeline can interpret log-derived evidence, identify insufficient or missing policy controls, and generate actionable remediation recommendations with explicit evidence-to-policy traceability. Unlike prior work that treats log analysis and policy validation as isolated tasks, this study integrates both into a unified end-to-end proof-of-concept post-incident review framework. The findings suggest that LLM-assisted analysis has the potential to improve the efficiency, consistency, and auditability of post-incident evaluations, while highlighting the continued need for human oversight in high-stakes cybersecurity decision-making. --- ### A Dynamic Retrieval-Augmented Generation System with Selective Memory and Remembrance Authors: Okan Bursa Published: 2026-01-04 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2601.02428v1 We introduce \emph{Adaptive RAG Memory} (ARM), a retrieval-augmented generation (RAG) framework that replaces a static vector index with a \emph{dynamic} memory substrate governed by selective remembrance and decay. Frequently retrieved items are consolidated and protected from forgetting, while rarely used items gradually decay, inspired by cognitive consolidation and forgetting principles. On a lightweight retrieval benchmark, ARM reaches near state-of-the-art performance (e.g., NDCG@5 $\approx$ 0.940, Recall@5 $=1.000$) with only $\sim$22M parameters in the embedding layer, achieving the best efficiency among ultra-efficient models ($<$25M parameters). In addition, we compare static vs. dynamic RAG combinations across Llama 3.1 and GPT-4o. Llama 3.1 with static RAG achieves the highest key-term coverage (67.2\%) at moderate latency, while GPT-4o with a dynamic selective retrieval policy attains the fastest responses (8.2s on average) with competitive coverage (58.7\%). We further present an engineering optimization of the DynamicRAG implementation, making embedding weights configurable, adjustable at runtime, and robust to invalid settings. ARM yields competitive accuracy, self-regularizing memory growth, and interpretable retention dynamics without retraining the generator\color{black} and provides practical trade-off between quality, latency and memory efficiency for production and research RAG system. --- ### NitroGen: An Open Foundation Model for Generalist Gaming Agents Authors: Loïc Magne, Anas Awadalla, Guanzhi Wang, Yinzhen Xu, Joshua Belofsky, Fengyuan Hu, Joohwan Kim, Ludwig Schmidt, Georgia Gkioxari, Jan Kautz, Yisong Yue, Yejin Choi et al. Published: 2026-01-04 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2601.02427v1 We introduce NitroGen, a vision-action foundation model for generalist gaming agents that is trained on 40,000 hours of gameplay videos across more than 1,000 games. We incorporate three key ingredients: 1) an internet-scale video-action dataset constructed by automatically extracting player actions from publicly available gameplay videos, 2) a multi-game benchmark environment that can measure cross-game generalization, and 3) a unified vision-action model trained with large-scale behavior cloning. NitroGen exhibits strong competence across diverse domains, including combat encounters in 3D action games, high-precision control in 2D platformers, and exploration in procedurally generated worlds. It transfers effectively to unseen games, achieving up to 52% relative improvement in task success rates over models trained from scratch. We release the dataset, evaluation suite, and model weights to advance research on generalist embodied agents. --- ### A large-scale nanocrystal database with aligned synthesis and properties enabling generative inverse design Authors: Kai Gu, Yingping Liang, Senliang Peng, Aotian Guo, Haizheng Zhong, Ying Fu Published: 2026-01-04 Categories: cond-mat.mtrl-sci, cs.AI arXiv: https://arxiv.org/abs/2601.02424v2 The synthesis of nanocrystals has been highly dependent on trial-and-error, due to the complex correlation between synthesis parameters and physicochemical properties. Although deep learning offers a potential methodology to achieve generative inverse design, it is still hindered by the scarcity of high-quality datasets that align nanocrystal synthesis routes with their properties. Here, we present the construction of a large-scale, aligned Nanocrystal Synthesis-Property (NSP) database and demonstrate its capability for generative inverse design. To extract structured synthesis routes and their corresponding product properties from literature, we develop NanoExtractor, a large language model (LLM) enhanced by well-designed augmentation strategies. NanoExtractor is validated against human experts, achieving a weighted average score of 88% on the test set, significantly outperforming chemistry-specialized (3%) and general-purpose LLMs (38%). The resulting NSP database contains nearly 160,000 aligned entries and serves as training data for our NanoDesigner, an LLM for inverse synthesis design. The generative capability of NanoDesigner is validated through the successful design of viable synthesis routes for both well-established PbSe nanocrystals and rarely reported MgF2 nanocrystals. Notably, the model recommends a counter-intuitive, non-stoichiometric precursor ratio (1:1) for MgF2 nanocrystals, which is experimentally confirmed as critical for suppressing byproducts. Our work bridges the gap between unstructured literature and data-driven synthesis, and also establishes a powerful human-AI collaborative paradigm for accelerating nanocrystal discovery. --- ### Watch Wider and Think Deeper: Collaborative Cross-modal Chain-of-Thought for Complex Visual Reasoning Authors: Wenting Lu, Didi Zhu, Tao Shen, Donglin Zhu, Ayong Ye, Chao Wu Published: 2026-01-04 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2601.02422v1 Multi-modal reasoning requires the seamless integration of visual and linguistic cues, yet existing Chain-of-Thought methods suffer from two critical limitations in cross-modal scenarios: (1) over-reliance on single coarse-grained image regions, and (2) semantic fragmentation between successive reasoning steps. To address these issues, we propose the CoCoT (Collaborative Coross-modal Thought) framework, built upon two key innovations: a) Dynamic Multi-Region Grounding to adaptively detect the most relevant image regions based on the question, and b) Relation-Aware Reasoning to enable multi-region collaboration by iteratively aligning visual cues to form a coherent and logical chain of thought. Through this approach, we construct the CoCoT-70K dataset, comprising 74,691 high-quality samples with multi-region annotations and structured reasoning chains. Extensive experiments demonstrate that CoCoT significantly enhances complex visual reasoning, achieving an average accuracy improvement of 15.4% on LLaVA-1.5 and 4.0% on Qwen2-VL across six challenging benchmarks. The data and code are available at: https://github.com/deer-echo/CoCoT. --- ### Learnability-Driven Submodular Optimization for Active Roadside 3D Detection Authors: Ruiyu Mao, Baoming Zhang, Nicholas Ruozzi, Yunhui Guo Published: 2026-01-04 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.01695v1 Roadside perception datasets are typically constructed via cooperative labeling between synchronized vehicle and roadside frame pairs. However, real deployment often requires annotation of roadside-only data due to hardware and privacy constraints. Even human experts struggle to produce accurate labels without vehicle-side data (image, LIDAR), which not only increases annotation difficulty and cost, but also reveals a fundamental learnability problem: many roadside-only scenes contain distant, blurred, or occluded objects whose 3D properties are ambiguous from a single view and can only be reliably annotated by cross-checking paired vehicle--roadside frames. We refer to such cases as inherently ambiguous samples. To reduce wasted annotation effort on inherently ambiguous samples while still obtaining high-performing models, we turn to active learning. This work focuses on active learning for roadside monocular 3D object detection and proposes a learnability-driven framework that selects scenes which are both informative and reliably labelable, suppressing inherently ambiguous samples while ensuring coverage. Experiments demonstrate that our method, LH3D, achieves 86.06%, 67.32%, and 78.67% of full-performance for vehicles, pedestrians, and cyclists respectively, using only 25% of the annotation budget on DAIR-V2X-I, significantly outperforming uncertainty-based baselines. This confirms that learnability, not uncertainty, matters for roadside 3D perception. --- ### Enhanced Multi-model Online Conformal Prediction Authors: Erfan Hajihashemi, Yanning Shen Published: 2026-01-04 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.01692v1 Conformal prediction is a framework for uncertainty quantification that constructs prediction sets for previously unseen data, guaranteeing coverage of the true label with a specified probability. However, the efficiency of these prediction sets, measured by their size, depends on the choice of the underlying learning model. Relying on a single fixed model may lead to suboptimal performance in online environments, as a single model may not consistently perform well across all time steps. To mitigate this, prior work has explored selecting a model from a set of candidates. However, this approach becomes computationally expensive as the number of candidate models increases. Moreover, poorly performing models in the set may also hinder the effectiveness. To tackle this challenge, this work develops a novel multi-model online conformal prediction algorithm that reduces computational complexity and improves prediction efficiency. At each time step, a bipartite graph is generated to identify a subset of effective models, from which a model is selected to construct the prediction set. Experiments demonstrate that our method outperforms existing multi-model conformal prediction techniques in terms of both prediction set size and computational efficiency. --- ### Mitigating Longitudinal Performance Degradation in Child Face Recognition Using Synthetic Data Authors: Afzal Hossain, Stephanie Schuckers Published: 2026-01-04 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.01689v1 Longitudinal face recognition in children remains challenging due to rapid and nonlinear facial growth, which causes template drift and increasing verification errors over time. This work investigates whether synthetic face data can act as a longitudinal stabilizer by improving temporal robustness of child face recognition models. Using an identity disjoint protocol on the Young Face Aging (YFA) dataset, we evaluate three settings: (i) pretrained MagFace embeddings without dataset specific fine-tuning, (ii) MagFace fine-tuned using authentic training faces only, and (iii) MagFace fine-tuned using a combination of authentic and synthetically generated training faces. Synthetic data is generated using StyleGAN2 ADA and incorporated exclusively within the training identities; a post generation filtering step is applied to mitigate identity leakage and remove artifact affected samples. Experimental results across enrollment verification gaps from 6 to 36 months show that synthetic-augmented fine tuning substantially reduces error rates relative to both the pretrained baseline and real only fine tuning. These findings provide a risk aware assessment of synthetic augmentation for improving identity persistence in pediatric face recognition. ---