AIの鬼

研究動向 (arXiv)

機械学習・自然言語処理・コンピュータビジョンの最新プレプリント。

cs.LGcs.AI

Gate-Zero Growth: A Geometric Framework for Function-Preserving Continual Learning

Dante Lok

We introduce \emph{gate-zero growth}, a function-preserving (FP) operator for continual learning that adds new residual blocks through a zero-initialised gate. Under a transversality condition, gate-zero growth induces \emph{rank separation} in the functional Jacobian: old directions are unchanged, new-weight directions are exactly flat at the growth point, and new gate directions are the only first-order source of new functional variation. As gates open during continual learning, function drift…

arXiv → PDF
cs.AIcs.CR

Democratizing Agent Deployment Safety: A Structural Monitoring Approach

Preeti Ravindra, Rahul Tiwari, Vincent Wolowski

AI software development agents are increasingly capable of modifying infrastructure and security critical systems, creating risks where an agent completes its assigned task while covertly weakening safeguards through actions such as broadening permissions, degrading logging, or introducing persistence mechanisms. While frontier laboratories may deploy sophisticated monitoring pipelines, many organizations and individual users adopting coding agents lack the resources and governance maturity requ…

arXiv → PDF
cond-mat.othercs.AI

A Modern Multimodal Assistant on a 6 GB 2011 GPU: Stage-Validated, All-GPU CUDA Inference for Fermi

A. C. Opus, J. Q. Lu

A companion study ran a 35B mixture-of-experts model on a 2011 NVIDIA Tesla C2075 (Fermi, sm_20, 6GB) as a GPU-prefill/CPU-decode hybrid, because the 4-bit model did not fit in device memory (arXiv:2606.24031). This report keeps the hardware and asks what a model that fits can do: we deploy MiniCPM-V-4.6, a modern multimodal assistant pairing a SigLIP2 vision encoder and window-attention merger (16x visual token compression) with a compact hybrid gated-delta-net backbone, entirely on the GPU. Th…

arXiv → PDF
cs.LGstat.ML

Probabilistic Physics-Informed Neural Networks for Estimating Heterogeneous Elastic Properties from Low-Resolution and Noisy Displacement Data

Tatthapong Srikitrungruang, Jaesung Lee

Estimating spatially heterogeneous elastic properties from low-resolution displacement measurements is a severely ill-posed inverse elasticity problem because low resolution obscures spatial details needed to distinguish heterogeneous property variations, and small measurement perturbations or fitting errors are amplified through inverse estimation. Existing inverse methods often rely on high-fidelity observations and manually prespecified loss weights, limiting their adaptability and making the…

arXiv → PDF
cs.CL

MARS: Multi-hop Adaptive Retrieval and SPARQL Generation for KGQA

Nikit Srivastava, Daniel Vollmers, René Speck, Nikolaos Karalis, Hamada M. Zahera, Axel-Cyrille Ngonga Ngomo

Large language models (LLMs) have demonstrated strong reasoning performance, but their tendency to hallucinate limits their reliability in knowledge-intensive tasks requiring up-to-date and grounded information. Combining knowledge graphs (KGs) with LLMs facilitates the use of explicit symbolic knowledge that can be continuously updated without costly fine-tuning, while benefiting from rapidly advancing LLM reasoning. We propose MARS, a scalable knowledge graph question answering (KGQA) approach…

arXiv → PDF
cs.CV

Breaking the Model Forgetting Cycle in Long-Incremental 3D Object Detection

Peisheng Qian, Jie Xu, Xulei Yang, Na Zhao

Incremental 3D object detection requires a detector to learn novel object classes while remembering previously learned ones over sequentially arriving data. Previous methods, primarily based on pseudo-labeling, perform reasonably in short-incremental stages but still suffer from severe model forgetting when dealing with long-incremental sequences. We investigate this failure and reveal a detrimental self-reinforcing cycle: data distribution shift of novel classes causes model forgetting on old c…

arXiv → PDF
cs.AI

Seeing the End at Step Zero: Accelerating Diffusion MLLMs via MLP Sparsity-Aware Truncation

Qicheng Zhao, Qi Sun, Zheyu Yan

Diffusion Multimodal Large Language Models (DMLLMs) are highly effective for multimodal reasoning, yet their inference efficiency is significantly hindered by fixed-length generation constraints. Since the actual output length is unknown, output sequences are padded to a predefined maximum length, resulting in substantial redundant computation over unnecessary [EOS] tokens. In this work, we discover that DMLLMs implicitly reveal their valid semantic boundary at the very first denoising step thro…

arXiv → PDF
cs.AIcs.MA

Towards an Intention Abstraction Layer for Autonomous Industrial Systems

Artan Markaj, Raphael Höfer, Felix Gehlhoff

Modern industrial environments increasingly run many autonomous subsystems at once - schedulers, energy managers, vehicle fleets - each pursuing its own goals while sharing the same physical resources. Because high-level human intentions are translated into low-level control logic and then discarded, no running component can tell whether it is still doing what was actually intended, and goal conflicts surface only after they have caused a missed target or a shutdown. We propose the Intention Abs…

arXiv → PDF
cs.CLcs.AI

Answer-Conditioned Chains of Thought Degrade Verifiable-Reasoning Distillation in Large Language Models

Jungseob Lee, Seungyoon Lee, Suhyune Son, Dongyub Jude Lee, Sungbin Han, Sugyeong Eo, Heuiseok Lim

A standard recipe for distilling the reasoning ability of large language models (LLMs) is to sample chains of thought from the model, keep those that reach the correct final answer, and fine-tune on the survivors. When sampling fails, a common fix shows the generator the gold answer and asks it to write a chain that reaches that answer. We show that this second step degrades the training data in a way that correctness filtering cannot catch. We run a controlled experiment that fixes the generato…

arXiv → PDF
cs.CV

HyMobileAgent: Data-Environment Co-Scaling for Efficient GUI Agents

Hy Vision Team, Huawen Shen, Zhengyang Tang, Shangpin Peng, Liang Wu, Anran Zhang, Weinong Wang, Yiduo Guo et al.

As large multimodal models move from understanding content to operating on digital environments, mobile GUI has emerged as a challenging and consequential testbed for digital embodied intelligence. Mobile agents operate under three coupled constraints: precise perception of complex interfaces, scalable acquisition of high-quality interaction data, and robust long-horizon decision making under compounding execution errors. This report presents HyMobileAgent, a mobile GUI agent built on Hy3.0-VL-A…

arXiv → PDF
cs.CV

AdaTurn: Budget-Aware Test-Time Scaling for Active Visual Perception Agents

Susan Liang, Chao Huang, Filippos Bellos, Jing Bi, Jason J Corso, Chenliang Xu

Active visual agents solve fine-grained image tasks by interleaving reasoning with image-grounding actions across multiple turns. However, deployment-time rollout budgets are rarely fixed: some requests permit long rollouts, while others require the agent to act under a tight turn limit. Existing methods train the policy as if the rollout budget were hidden, so when the available budget is smaller than the trajectory the agent prefers, the interaction is often truncated before any valid answer i…

arXiv → PDF
cs.LG

CASP: Learning-Augmented Offline Approximation with Verifiable Certificates and Bounded-Loss PAC Guarantees

Haifeng Li, Mo Hai

Machine-learned predictions can speed up offline NP-hard optimization, but asking a predictor what to do amounts to asking it to solve the problem, and committing an unchecked prediction forfeits every worst-case guarantee. CASP (Certificate-Augmented Solution Pruning) instead asks which parts of the search space may be ignored, and accepts each answer only after a sound polynomial-time verifier has checked it, so correctness never depends on prediction quality. We develop the learning theory of…

arXiv → PDF
cs.CV

3D Geometric Tooth Alignment Planning via Deep Reinforcement Learning

Yong Li, Jianwen Lou, Jiayue Ma, Yao-Xiang Ding, Youyi Zheng, Haihua Zhu

3D geometric tooth alignment planning, which determines sequential trajectories from initial malocclusion to the final target alignment, is a cornerstone of modern digital orthodontics. This paper presents a novel deep reinforcement learning (DRL) framework to automate the generation of these alignment paths. We formulate the planning process as a Markov Decision Process (MDP) to capture its sequential decision-making nature, focusing on optimizing geometric trajectories while integrating essent…

arXiv → PDF
cs.ROcs.AI

SafeRelBench: A Spatial-Relation-Aware Benchmark for Process-Level Safety in VLM-Driven Embodied Agents

Huaigang Yang, Ya Li, Min Ren, Bo Dai, Zhenliang Zhang, Zhaofeng He

Vision-language models (VLMs) are increasingly used as the reasoning backbone of embodied agents, enabling robots to interpret visual scenes, follow language instructions, and plan multi-step actions. In household environments, however, safety depends not only on recognizing objects, but also on how actions change the physical scene over time. Existing embodied safety evaluations largely focus on static risk recognition, unsafe instruction refusal, or final-state task completion. As a result, pr…

arXiv → PDF
cs.CL

CityLLM: A framework for natural-language querying of semantic 3D city models

Rabindra Lamsal, Sisi Zlatanova, Johnson Xuesong Shen

Semantic 3D city models provide rich geometric and semantic information, but remain challenging for non-experts and interdisciplinary researchers to access and query due to their complex structures and specialized data formats. To address this issue, we present CityLLM, a framework for natural-language querying of semantic 3D city models alongside complementary urban datasets. The framework combines spatial and graph databases within an LLM-based workflow that supports iterative query refinement…

arXiv → PDF
cs.AI

Are LLM-Generated GPU Kernels Production-Ready? A Trace-Driven Benchmark and Optimization Agent

Lingyun Yang, Yuxiao Wang, Shenghao Liang, Linfeng Yang, Daocheng Ying, Chunbo You, Rui Zhang, Luping Wang et al.

Existing GPU kernel generation benchmarks draw problems from synthetic or curated sources that diverge from deployed workloads. We present Atrex-Bench, a benchmark whose 30 operators and 440 shapes are sampled directly from full-cluster production inference traces of compute-limited, memory-rich GPUs. Each problem carries an importance weight derived from its share of observed GPU time, weighted by application card-hours and computed separately for the serving phases in which it runs, together w…

arXiv → PDF
cs.SDcs.LGeess.AS

MIDI-RAE-JEPA: Hierarchical Representation Learning and Generation for Symbolic Music

Scott H. Hawley

Rich internal representations of musical structure are essential for music understanding tasks such as machine-assisted music co-writing, yet self-supervised approaches for symbolic music representation remain underexplored, particularly those that encode the hierarchical multiscale nature of musical structures. We present MIDI-RAE-JEPA, combining a pitch- and time-shift equivariance objective with LeJEPA and a Swin Transformer V2 encoder to learn such hierarchical representations of symbolic mu…

arXiv → PDF
cs.LG

Muse: Representation Geometry of Muon Beyond Normalized Momentum

Da Chang, Qiankun Shi, Lvgang Zhang, Di He, Yaoshuai Ma, Ganzhao Yuan, Yongxiang Liu

Muon-style optimizers apply a polar map to matrix momentum, but their updates also depend on the representation of each parameter block before orthogonalization. We study this representation choice as a form of optimizer geometry and introduce {\method}, a family of Muon-style optimizers that shares the same momentum rule and Newton--Schulz backend across native, nearest-square, skinny, and vector representations. Each Frobenius-isometric representation induces a distinct polar steepest-descent…

arXiv → PDF
cs.CV

SwinAD: Multi-stage feature reconstruction for unsupervised industrial anomaly detection

Huong Ninh, Chien Thai, Mai Xuan Trang, Vu-Minh Le, Thanh Ha Le, Long Tran

Industrial anomaly detection aims to identify and localize defective regions without relying on exhaustive annotations of all possible defect types. Although recent unsupervised methods have achieved strong performance, most are primarily designed for single-class settings and often struggle in multi-class scenarios, where diverse normal patterns may lead to over-generalization and reduce the discriminative capability between normal and anomalous regions. In this paper, we propose SwinAD, a reco…

arXiv → PDF
cs.LGcs.CL

xHC: Expanded Hyper-Connections

Xiangdong Zhang, Xiaohan Qin, Sunan Zou, Tuo Dai, Xiaoming Shi, Huaijin Wu, Yebin Yang, Zhuo Xia et al.

Hyper-Connections (HC) expand the residual stream of Transformers into $N$ parallel streams, providing a form of memory scaling beyond model width and depth. Manifold-Constrained HC (mHC) stabilizes this formulation at scale. The large gains from $N{=}1$ to $N{=}4$ suggest residual-stream expansion as a promising scaling axis. However, existing HC-family methods typically stop at $N{=}4$. Our experiments reveal why: scaling mHC beyond this point yields diminishing performance gains and rapidly i…

arXiv → PDF
cs.CLcs.AI

Controlled Reformulation Testing for Logical Consistency in Large Language Models

Alexander Gu, Alan Chen

Large language models (LLMs) frequently contradict themselves when the surface form of a logically equivalent question changes. We present a benchmark of 350 question families (1,750 total questions) for Controlled Reformulation Testing (CRTBench) to evaluate logical invariance. In this benchmark, we investigate LLMs' ability to maintain consistent answers across controlled reformulations, which include contrapositive rewriting, double negation, negation flipping, and passive voice. We evaluate…

arXiv → PDF
math.APcs.LG

Riesz-Kernel Stein Variational Gradient Descent: Renormalized Entropy and Long-Time Particle Limits

Trevor Teolis, Maarten V. de Hoop

Stein variational gradient descent (SVGD) transports interacting particles toward a target distribution through deterministic kernelized dynamics. Singular Riesz kernels are attractive because they can provide quantitative population-level convergence, but at the finite-particle level the corresponding Stein energy has infinite self-interaction. We study periodic Riesz SVGD with self-interaction removed and prove a many-particle, long-time sampling theorem. Throughout the range in which the sing…

arXiv → PDF
cs.AIcs.CL

WrAFT: a Modularized Automated Writing Evaluation System for Argumentative Essays

Adnan Labib, Yixuan Huang, Jiahui Wu, John Maurice Gayed, Zheng Yuan, Qiao Wang

This study presents WrAFT, a Writing Assessment and Feedback Tool, that delivers both accurate and reliable scores and effective comprehensive feedback to argumentative essays. WrAFT adopts a modular design by dividing automated writing evaluation (AWE) tasks into scoring, surface-level feedback, and deep-level feedback. In building the system, various Large Language Models (LLMs) have been evaluated, including LLaMA-3.3-70B-Instruct, GPT-4o, and Claude 3.7, through both direct prompting and sup…

arXiv → PDF
cs.LG

A Continuous-Time Reinforcement Learning Framework for Fine-Tuning Discrete Diffusion Models

Zikun Zhang, Jiayuan Sheng, David D. Yao, Wenpin Tang

We formulate reinforcement learning (RL) in continuous time with discrete state spaces and possibly arbitrary action spaces via a stochastic control approach, where the state dynamics are modeled as a controlled continuous-time Markov chain (CTMC). We consider policy optimization problems and derive the corresponding policy gradient methods, leading to continuous-time variants of proximal policy optimization (PPO) and group relative policy optimization (GRPO). As a primary application, we develo…

arXiv → PDF
cs.CV

Uni-AdaVD: Universal Concept Erasure for Visual Generation via Orthogonal Value Decomposition

Qifan Zhou, Yuan Wang, Yanbin Hao, Xiang Wang, Kuien Liu, Richang Hong, Meng Wang

Visual generative models inevitably absorb undesirable concepts from uncurated pretraining data, making concept erasure essential for safe deployment. Existing erasure methods, however, are often architecture-specific and struggle to remove target concepts while preserving non-target content and generative priors. We present Uni-AdaVD, a universal inference-time concept erasure framework for visual generation. Uni-AdaVD treats the value space of multimodal attention as a unified intervention spa…

arXiv → PDF
cs.LGmath.OCstat.ML

Adaptive Runge-Kutta Step Control Buys Training Loss, Not Generalization: An Honest Compute-Matched Study of RK-Adam Optimizers

Akhilesh Gogikar

Interpreting optimizers as gradient-flow discretizations has motivated applying higher-order Runge-Kutta (RK) integrators to neural networks. We build a representative Adam variant (Bogacki-Shampine 3(2) RK pair, FSAL reuse, local-error step control) and evaluate it under a strict compute-matched protocol giving every method the same gradient-evaluation budget - an accounting this literature rarely enforces. Under it the RK variant loses to plain Adam on training loss in both minibatch and full-…

arXiv → PDF
cs.CVcs.AI

VTM-Nav: Hierarchical Visual-Topological Memory for Cross-Episode Object-Goal Navigation

Xiaoran Xu, Yupeng Wu, Tianyu Xue, Yifan Xu, Xuanran Dong, Xiaoshan Yang, Changsheng Xu

Object-goal navigation requires an embodied agent to locate and reach an instance of a specified object category in an indoor environment. Recent training-free approaches leverage vision-language models (VLMs) for open-vocabulary semantic reasoning, but are typically evaluated under an episodic protocol that resets all scene-specific state after each episode. We introduce Cross-Episode Object-Goal Navigation, in which an agent repeatedly operates in the same scene, retains only self-acquired exp…

arXiv → PDF
cs.CVeess.IV

Compression of 3D Gaussian Splatting Data Using GPU-friendly Graphics Texture Coding

Amir Said, Randall Rauwendaal

Techniques for modeling 3D scenes from image collections, such as 3D Gaussian Splatting (3DGS), are capable of generating high-quality novel views by leveraging graphics primitives with view-dependent appearance. In 3DGS, spherical harmonic (SH) are employed to model view-dependent color, resulting in a large number of SH coefficients per primitive and large memory requirements. While compression approaches have been proposed to mitigate this problem, they do not exploit the capabilities of mode…

arXiv → PDF
cs.AIcs.CLcs.LG

RetroAgent: Harnessing LLMs to Search Over Structured Memory for Agentic Retrosynthesis Planning

Yanqiao Zhu, Jingru Gan, Xiaoqi Sun, Fang Sun, Yidan Shi, Md Mofijul Islam, Chao Shang, Wenhao Gao et al.

Multi-step retrosynthesis planning seeks to decompose a target molecule into commercially available building blocks through a sequence of feasible reactions. The vast combinatorial search space makes this task challenging even for expert chemists. Traditional methods combine tree search with offline-trained value networks that score candidates in isolation, without reasoning about complete multi-step routes. Recent work leverages Large Language Models (LLMs) for this task, but relies on simple i…

arXiv → PDF
cs.AI

VLT: A Vision-Language-Time Series Multimodal Foundation Model for Industrial Intelligence

Haiteng Wang, Jingheng Yan, Xiaokang Wang, Lei Ren

Industrial time series serve as the foundation for Prognostics and Health Management (PHM) to ensure the reliability and safety of industrial equipment such as aero-engines. However, existing approaches are typically limited to single-modality modeling, which restricts their generalization in complex scenarios. Although recent advances in large language models (LLMs) provide new opportunities for multimodal learning, bridging continuous time-series signals and discrete textual semantics remains…

arXiv → PDF