Computer Vision
After a Decade: Bringing Shadow Removal into the Real World with Agentic Training Data
Shilin Hu, Jingyi Xu, Dimitris Samaras et al. (+1 more)
Shadow removal looks nearly solved on established
benchmarks, yet remains brittle in the real world. Models have advanced; the paired training data they rely on have barely changed in nearly a decade. The reason is simple: obtaining a shadow-free target requires removing the occluder while keeping the scene, camera, and illumination otherwise unchanged, making diverse paired data difficult to capture. Meanwhile, large shadow detection
datasets already contain diverse real-world images and masks, but no shadow-free targets. To turn this abundant but incomplete data into paired supervision, we propose an offline agentic workflow combining physics-motivated generation, failure detection, feedback-driven retry, candidate selection, and deterministic correction. Using this workflow, we construct AgenticShadow, a
dataset of 17,138 image-mask-target triplets spanning general scenes, faces, and remote sensing. Our construction workflow reduces Color Distribution Difference by 50.5% over previous shadow removal work, while training existing shadow removal models on AgenticShadow reduces cross-domain LAB RMSE by 19.7-37.5%.
Read the full abstract ▾
All authors Shilin Hu, Jingyi Xu, Dimitris Samaras, Hieu Le
Cryptography and Security
SecureVibe: Making Vibe Coding More Secure
Danqing Wang, Baolin Peng, Zhepei Wei et al. (+8 more)
As vibe coding becomes increasingly capable and widespread, security vulnerabilities in even functionally correct solutions are a growing concern. When investigating functionally correct but insecure solutions, we find that the insecure
agent is less than half as likely to conduct effective planning and testing for the hidden security risks behind the functional requirements. Motivated by this, we develop SECUREVIBE, a training recipe that explicitly targets planning and testing for code security. SECUREVIBE constructs training signals around these security behaviors. It includes supervised fine-tuning on the security suite with 4 security tasks, and post-training methods, SECUREVIBE_rl and SECUREVIBE_hg, to enhance security capabilities from verifiable execution feedback and hint-based self-supervision. Our SECUREVIBE outperforms the baseline on two types of security coding tasks across 4
benchmarks. Specifically, SECUREVIBE improves the security pass@1 by 6.9 points on BaxBench. The gains extend to unseen CWE categories, with improvements of 11.5 points on SusVibes. Meanwhile, it also improves functionality pass@1 by 13.6 points on the security coding task SusVibes and 4.1 points on the generic coding task SWE-bench Verified. Further analysis offers two practical insights: (i) diversifying supervision across security planning, coding, and testing strengthens security behaviors more effectively than adding coding trajectories alone, and (ii) hint-guided supervision is particularly valuable when the
agent's existing security capabilities are insufficient to learn effectively from outcome feedback.
Read the full abstract ▾
All authors Danqing Wang, Baolin Peng, Zhepei Wei, Isadora White, Wenlin Yao, Hao Cheng, Qianhui Wu, Minseon Kim, Xingdi Yuan, Lei Li, Jianfeng Gao
Computation and Language
Beyond Oracle Communication: Benchmarking Interactive Intent Alignment Under Miscommunication and Evolving User Intent
Zheyuan Zhang, Mengyuan Chao, Ke Xiao et al. (+5 more)
Modern LLM
agents increasingly tackle complex tasks through interactive, long-horizon exchanges with users, while existing
benchmarks generally assume that users always accurately and sufficiently communicate a fixed intent. However, this oracle communication assumption rarely holds in practice: users may miscommunicate, change their goals, and run out of patience. We define this task setting as Interactive Intent
Alignment, where
agents must recover and continuously track the user's current intent despite imperfect communication and evolving goals. To study this setting, we introduce Drift-Bench++, a principled
benchmark construction pipeline for verified executable tasks with controlled misalignment and intent shifts, along with an interaction protocol featuring finite patience, diverse simulated users, and silent interaction-conditioned shifts. We further develop GRIP, a comprehensive evaluation protocol covering task grounding, user realism, inquiry effectiveness, and adaptation to evolving intent. Across diverse environments, models, and interaction conditions, stronger interaction consistently helps but remains far from oracle performance; Validation on deployed ProdAgent sessions further shows that the modeled failures are prevalent and consequential in deployment. By providing a unified, executable
benchmark for interactive intent
alignment, Drift-Bench++ offers a foundation for evaluating and advancing
agents under realistic communication and evolving intent.
Read the full abstract ▾
All authors Zheyuan Zhang, Mengyuan Chao, Ke Xiao, Ziyi Chen, Daoan Zhang, Yan Zhang, Yanfang Ye, Wei Xu
Computer Vision
Aperture: Training-Free Multiscale Concept Bottlenecks for Remote Sensing
Rishabh Mondal, Nipun Batra and Utkarsh Mall
While earth observation models have advanced substantially, they still lack interpretability. While concept-bottleneck models provide interpretability and expert interaction, they are either too expensive to train for the remote sensing domain or perform poorly without annotation. We posit that in expert domains like remote sensing, such training-free models require both fine details in both image and concept space. In image space, we propose a multiscale concept bottleneck using greedy quadtree routing to locate small concepts. In concept space, we replace contrastive
vision language models with pre-trained MLLMs and present a way to get reliable concept scores from them. We introduce APERTURE that blends concept scores at the global image and native concept-scale level to give state-ofthe-art training-free model performance. To test these models, introduce SiFC, a fine-grained concept-centric
dataset across three countries, with human-reviewed class-level concept maps. On SiFC, APERTURE outperforms the best training-free baselines by more than 10 percentage points in macro F1-score, and notably also outperforms supervised concept bottleneck models. Targeted component-removal tests examine whether concept scores respond to changes in visual evidence, while temporal experiments show that descriptor updates improve recognition of technological changes without retraining.
Read the full abstract ▾
Systems and Control
VHF Reconfigurable Intelligent Surfaces for Meteor Burst Communication
Rajiv Thummala, Luke Flores and Gregory Falco
Meteor Burst Communication (MBC) utilizes the transient ionized trails left by meteors to reflect Very High Frequency (VHF) signals, enabling long-range, beyond-line-of-sight communication without reliance on terrestrial or satellite infrastructure. Despite its resilience in austere and contested environments, MBC is limited by brief communication windows, low signal-to-noise ratio (SNR), and inconsistent channel availability. Recent advancements in Reconfigurable Intelligent Surfaces (RIS) offer a transformative solution by enabling dynamic control over signal propagation through programmable reflective elements. This paper proposes a novel system architecture that integrates RIS into MBC networks, incorporating real-time adaptive control, optimized deployment strategies, and Monte Carlo simulations to refine RIS placement and operational parameters.
Read the full abstract ▾
Hardware Architecture
Structure-augmented LLMs for High-Level Synthesis Pragma Optimization
Haocheng Xu, Ye Qiao, Phyo Pyae Moe Aung et al. (+7 more)
Pragma insertion drives the quality of high-level synthesis (HLS) designs. Choosing the right directives demands expert knowledge and
reasoning about loop nesting, data dependences, and
memory layout. While existing large
language models (LLMs) show promise in code generation, they lack explicit program-structure awareness, limiting their ability to suggest effective pragmas. We present PRISM, a novel structure-augmented LLM that closes this gap by adding compiler-grade structural
reasoning to a pretrained, frozen code LLM. It combines three hierarchical program representations, Abstract Syntax Tree (AST), Control-Flow Graph (CFG), and Data-Flow Graph (DFG), injecting them into a specific
transformer layer while keeping original code
tokens in a separate stream. The cross-
attention gate at the injection point allows falling back to the pretrained representation when its structural signal is unhelpful. On zero-shot evaluation in HLS-Eval, PRISM synthesizes 3.5\times as many kernels as Llama3-8B (26.9% vs. 7.7%), and on the kernels where it does succeed, it produces designs that are 2.31\times faster (geomean) than GPT-5-mini's. In the agentic flow, the PRISM codegen outperforms other baselines when optimizing complex code and drives the average normalized improvement across the HLS-Eval suite to 26.4%.
Read the full abstract ▾
All authors Haocheng Xu, Ye Qiao, Phyo Pyae Moe Aung, Alok Mishra, Pavana Prakash, Rolando Pablo Hong Enriquez, Adam Han Wu, Zhiheng Chen, Dejan Milojicic, Sitao Huang
Artificial Intelligence
Sense and Sensitivity: Benchmarking LLM Clinical Triage Recommendations with Physician Experts
Abinitha Gourabathina, Haoran Zhang, Yuexing Hao et al. (+2 more)
As large
language models (LLMs) are increasingly used in clinical settings, it is critical to evaluate their reliability under realistic variation in clinical text. We study this question in clinical triage, comparing LLMs to practicing physicians under text perturbations that preserve the underlying clinical setting. We introduce a
benchmark of over 6,000 clinical scenarios, 7,000 physician annotations, and 225,000 model responses. Using this
benchmark, we make two key observations. First, LLMs are more likely than physicians to recommend unnecessary care at baseline, and this tendency increases under perturbed inputs. Further, we find that LLM recommendations are more sensitive to gender and tone perturbations than human recommendations. Together, these results demonstrate that LLMs can vary under clinically irrelevant textual changes, highlighting the need for deployment-oriented evaluations grounded in expert physician behavior.
Read the full abstract ▾
All authors Abinitha Gourabathina, Haoran Zhang, Yuexing Hao, Walter Gerych, Marzyeh Ghassemi
Machine Learning
JARQ: Joint Alternating Refinement for Quantization
Xinyu Wang, Sicheng Lyu and Xiao-Wen Chang
Group-wise post-training quantizers for large
language models round weights onto a grid that is not refit to the resulting integer codes. We show that this leaves accuracy on the table: the best grid depends on the codes, input correlations couple the errors of different groups, and useful code changes often involve many codes at once. We propose JARQ , a plug-in refinement that starts from any group-wise quantizer and alternates a joint least-squares fit of all group scales with bounded Babai proposals that move many codes of a group together on the current grid. The problem is a bilinear box-constrained mixed-integer least-squares problem; the solver is backpropagation-free, does not increase the layer-wise objective under exact scale solves, and keeps the host's bit width, groups, zero points, and inference cost. Across Llama-2, Llama-3, and Qwen models with RTN, GPTQ, OmniQuant, and AWQ hosts, JARQ lowers perplexity in 90 of 96 comparisons, cuts three-bit RTN perplexity by up to 36%, raises mean multiple-choice accuracy in 23 of 24 configurations, and improves QEP, QuaRot, and OJBKQ outputs, at under a minute per 7B block.
Read the full abstract ▾
Machine Learning
Reinforcement Learning with Complex (valued) Memories
Sathya Kamesh Bhethanabhotla, Efstratios Gavves and André Biedenkapp
Partially observable environments pose a fundamental challenge in deep reinforcement learning, requiring
agents to compress temporal information from observations and maintain a
memory to make effective decisions. While there exist many approaches ranging from gated recurrence to
attention mechanisms and model-based RL, the search for effective representational techniques that can capture long-term dependencies remains an active area of research. In this work we revisit
Unitary recurrent networks (uRNNs) [Arjovsky et al., 2016, Jing et al., 2017], that demonstrated superior gradient flow and associative recall, expressing the recurrence and the hidden state in a complex vector space. Their norm preserving
unitary dynamics enable information propagation through long sequences. To this end, we propose three different versions of uRNNs as drop-in replacements for recurrent PPO architectures, and demonstrate that the simple recurrence and the added degree of freedom from the phase of the complex representations enable significant gains over baselines on several
memory-improvable tasks, including continuous control. We further explore how to preserve the phase information of the complex hidden state for a phase-aware policy by drawing a parallel to how
quantum states are measured. With our methods reaching up to 2-3 $\times$ the reward in environments like rocksample and Craftax compared to the baselines, this work points towards an exciting new direction of representations for RL and the problem of partial observability. Code is available at: https://github.com/Sathya98/qurl
Read the full abstract ▾
Computer Vision
PixelUMM: Encoder-Free Unified Image and Video Understanding and Generation
Cong Wei, Xuanchi Ren, Bryan Chu et al. (+8 more)
Unified
Multimodal Models (UMMs) often rely on separate visual representations for understanding and generation, increasing visual context length and complicating integration with established
vision-
language pretraining pipelines. Recent advances in pixel-space modeling offer an encoder-free alternative, but extending this paradigm from images to
videos is non-trivial:
video understanding and generation adopt different temporal representations, leaving the design of a unified visual interface an open question. We present PixelUMM, an encoder-free model for unified image and
video understanding and generation directly in pixel space. PixelUMM represents images as spatial patches and
videos as spatiotemporal tubelets, connecting raw pixels to a shared
multimodal backbone through single-layer linear projections. Its Mixture-of-
Transformers architecture combines shared
attention with task-specific parameters and extends clean-pixel prediction to
video generation, jointly supporting autoregressive text prediction and pixel-space flow matching. Experiments show that PixelUMM achieves competitive performance across image and
video understanding and generation tasks. We further conduct empirical studies of key design choices, including decoder design and spatial-temporal patch size, providing insights for future pixel-space unified
multimodal models.
Read the full abstract ▾
All authors Cong Wei, Xuanchi Ren, Bryan Chu, Weiming Ren, Huan Ling, Jiahui Huang, Laura Leal-Taixé, Sanja Fidler, Wenhu Chen, Zian Wang, Jay Zhangjie Wu
Robotics
FAST-Sync: Fast Group Synchronization for any Matrix Lie Group
Shane Holmes, Yiran Luo, Firat Taxpulat et al. (+2 more)
Group synchronization (GS) is the problem of estimating a set of $N$ unknown elements $g_1,\ldots, g_N \in \mathcal{G}$ in a group $\mathcal{G}$, given noisy measurements of a subset of their pairwise ratios $g_i^{-1} g_j$. GS problems lie at the core of many state estimation tasks in robotics and computer
vision, including 3D
vision, robotic mapping, inertial
navigation, and molecular reconstruction. Unfortunately, GS problems are typically both high-dimensional and non-convex, and therefore hard to solve in general. In this paper, we present Fast-Sync, a fast linear approximation method for GS that is suitable for initializing local
manifold-based optimizers or certifiable global methods. Our approach generalizes chordal initialization to arbitrary
matrix Lie groups, and additionally proposes two new key algorithmic enhancements: we show how to exploit both the Kronecker-product structure in the problem data
matrix and the
topology of the synchronization graph to improve speed, scalability, and accuracy. Experimental evaluation across several GS tasks demonstrates that Fast-Sync provides high-quality initializations that enable local optimizers to efficiently recover globally optimal GS solutions, achieving high success rates even with considerable measurement noise.
Read the full abstract ▾
All authors Shane Holmes, Yiran Luo, Firat Taxpulat, David M. Rosen, Frank Dellaert
Computation and Language
Prompt2Skill: Unsupervised Skill Optimization From Natural Language Instructions
Bo Ni, Li Li, Ryan A. Rossi et al. (+2 more)
Skills are external artifacts that Large
Language Models (LLMs) consume at inference time to improve their performance on specialized domains by incorporating relevant procedural and domain knowledge. Expert-authored skills are expensive to produce, and the resulting artifacts are not optimized for the specific model that consumes them, whose failure modes can vary with version, scale and training. In addition, emerging tasks may fall outside the scope of existing skill libraries, creating a need to develop new skills before curated training data become available. Recent works have explored automated skill optimization through reflection, but they require a curated, in-distribution training set, which users might not always have. To address these limitations, we present
Prompt2Skill, a framework that builds skills from natural-
language task description alone. From the
prompt, the system derives a task specification, discovers or synthesizes
datasets, and refines the skill in a closed loop of reflective editing. Across four domains spanning question answering, reading comprehension, spreadsheet manipulation, and mathematical
reasoning,
Prompt2Skill consistently outperforms the direct prompting baseline, achieving an average improvement of 10.8 across open-source and frontier models.
Read the full abstract ▾
All authors Bo Ni, Li Li, Ryan A. Rossi, Franck Dernoncourt, Tyler Derr
Computer Vision
StereoGaussians: Feed-Forward 3D Gaussian Splatting from Stereo Images
Boyuan Tian, Huangying Zhan, Zhan Li et al. (+4 more)
Feed-forward 3D Gaussian Splatting (3DGS) enables reconstruction without per- scene optimisation, but practical stereo-camera applications require nearby-view extrapolation beyond the input views. Stereo depth anchors visible surfaces, yet rendering newly exposed regions also requires learned appearance and additional scene capacity. We introduce StereoGaussians, which predicts a metric 3DGS representation from a single calibrated stereo pair. It reuses intermediate repre- sentations from frozen pretrained stereo networks to predict Gaussian attributes, while calibrated disparity anchors the geometry. A second Gaussian layer and an expanded image canvas provide capacity for disoccluded and outside-field-of- view content. For training, we construct SceneSplat-Stereo from quality-filtered 3DGS teachers, pairing stereo inputs with nearby target views across 803 training scenes. Experiments on unseen real and photorealistic stereo
benchmarks demon- strate improvements over strong view-synthesis baselines, while ablation studies support our main design choices.
Read the full abstract ▾
All authors Boyuan Tian, Huangying Zhan, Zhan Li, Shin-Fang Chng, Hanwen Yang, Zirui Wang, Yi Xu
Computer Vision
Restoring without Forgetting: Filter-Level Continual Image Restoration via Parameter-Space Integrated Gradients
Xin Feng, Jin Zhao, Yizhen Zhang et al. (+3 more)
Adapting image restoration models to a stream of new tasks without revisiting past data remains challenging due to catastrophic forgetting. In this work, we propose Restoring without Forgetting (RwF), a filter-level continual adaptation framework for image restoration built upon a critical observation: task-specific knowledge is centered in a small subset of filters and can be separated from those reconstructing general content. RwF first performs parameter-space integrated gradients attribution to localize degradation-critical filters in a coarse-to-fine manner. It then adapts to new tasks by generating task-specific filters from a filter bank using compact factorized low-rank transformations, further augmented with cross-task
attention and prototypical contrastive learning, and lastly assembles them back only at localized positions. Experiments on six restoration tasks show that RwF effectively avoids forgetting and achieves competitive restoration quality against all-in-one methods that have full data access, and outperforms LoRA-style adaptation with $\sim$10$\times$ fewer additional parameters. Code is available at https://github.com/funkdub/Restoring-without-Forgetting.
Read the full abstract ▾
All authors Xin Feng, Jin Zhao, Yizhen Zhang, Wenjie Pei, Fanglin Chen, Guangming Lu
Human-Computer Interaction
C-LISTEN: Cognitive Load Impacts of Sensory-Triggered Environmental Navigation in Virtual Reality
Md. Monowar Hossain and M. Rasel Mahmud
Nowadays, Virtual Reality (VR) systems are more helpful for making decisions, training, and rehabilitation.
Multimodal settings in these systems impose a significant balance and cognitive difficulties. Additionally, decreased performance, higher cognitive load, user overwhelm, and limited accessibility of VR technology can be caused by excessive auditory, visual, and sensory stimulation. In our pilot study, we examine the strategic design of directional auditory cues to improve cognitive load and enhance user experience in virtual environments. This research also enhances fundamental knowledge that auditory feedback reduces cognitive load in VR, with statistical analysis confirming this improvement (p = .0011). This study investigates how postural balance and pupil diameter correlate with cognitive load while the users navigate. Moreover, this study provides realistic overview design guidelines for accessibility, which will make VR experiences safer and more useful for everyone, including people with cognitive impairments.
Read the full abstract ▾
Robotics
Drone Soccer: Learning to Manipulate with Multicopter Downwash
Neelay Joglekar, Bavin Saravanan, Yutong Wang et al. (+3 more)
Although multicopter drones are traditionally designed for "perception-only" tasks, like mapping and exploration, recent work has sought to develop Unmanned Aerial Manipulators (UAMs) to solve mobile manipulation tasks. Aerial manipulation performance can be impacted by "downwash," the airflow produced by propellers, but current state-of-the-art UAMs either ignore downwash or treat it as a disturbance. Instead, is it possible to actively use downwash as a tool during manipulation? We design a drone soccer task to explore the feasibility of downwash-based manipulation. Specifically, we develop a simplified downwash dynamics model which we use to train an RL policy to dribble a soccer ball. We further demonstrate that our policy transfers to real world deployment. This work provides key insights into novel manipulation capabilities for multicopters.
Read the full abstract ▾
All authors Neelay Joglekar, Bavin Saravanan, Yutong Wang, Varun Kandiyappan, Junyi Geng, Sebastian Scherer
Machine Learning
NeurDuo-EEG: A Long-Sequence EEG Foundation Model with Persistent State and Explicit Memory
Yifan Wang, Haiping Liu, Yang Cui et al. (+13 more)
Electroencephalography (
EEG) is recorded continuously over hours, with relevant dynamics spanning timescales from milliseconds to hours. Most
EEG foundation models nevertheless process fixed windows independently, limiting their ability to capture information encoded in long-timescale dynamics. State-space architectures enable persistent recurrent processing, but long-range information remains implicitly compressed in recurrent states. We present NeurDuo-
EEG, a causal
EEG foundation model with channel-resolved persistent
memory. NeurDuo-
EEG introduces multi-timescale
memory management with learned consolidation and selective
retrieval, enabling persistent modelling of continuous
EEG with fixed-size state. It is pre-trained on 3,955 hours of
EEG from 17 public
datasets using multichannel autoregressive prediction of discrete spectral codes. Across three short-window and two long-sequence downstream tasks, NeurDuo-
EEG achieves the best performance on four of five
benchmarks, including all three short-window tasks and seizure detection, where AUC-PR improves from $0.285$ to $0.471$ over the strongest non-NeurDuo baseline. NeurDuo-
EEG also remains competitive on sleep staging and supports efficient streaming inference, with nearly constant per-chunk latency as the available history grows to one hour. Notably, the Small variant achieves this with only 4.7M backbone parameters. These results demonstrate the value of persistent, multi-timescale modelling for both long-sequence and short-window
EEG analysis. Our code is available at https://github.com/YifaNNW/NeurDuo-
EEG.
Read the full abstract ▾
All authors Yifan Wang, Haiping Liu, Yang Cui, Wenhao Cai, Shuhang Li, Xiaoyang Huang, Xianyang Liu, Jingyu Sun, Yizheng Sun, Cunhang Fan, Tianming Du, Jiancheng Yang, Zhenhong Li, Yunhao Zhang, Hongpeng Zhou, Jingyuan Sun
Machine Learning
FlexRouter: Learning Complementary Model Sets for Flexible LLM Routing
Wang Wei, Harry Yang, Tiankai Yang et al. (+6 more)
Existing Large
Language Model (LLM) routing methods score LLMs independently to select top-$k$ models. However, this ignores model correlations and enforces a rigid computational budget. Consequently, routers often select redundant models that share failure modes, limiting the overall probability of success. To address this, we propose FlexRouter, a routing framework that explicitly models model complementarity. FlexRouter optimizes for answer coverage, maximizing the probability that at least one selected model yields a correct response. This objective aligns with practical inference pipelines where multiple candidate outputs are generated and a downstream verifier or user selects the final one. We formulate routing as a coverage-oriented subset selection problem and model the routing policy using Determinantal Point Processes (DPPs), which naturally capture both model competence and redundancy. To directly optimize coverage without requiring a ground-truth target subset, we introduce a training objective based on marginalizing over failure sets. During inference, we employ a greedy strategy based on marginal log-determinant gains, enabling the router to adaptively determine subset sizes without a predefined budget. Extensive experiments on the large-scale RouterEval
benchmark demonstrate that our proposed FlexRouter achieves higher coverage with lower redundancy across both in-domain and out-of-domain tasks than strong baselines while maintaining flexible inference cost.
Read the full abstract ▾
All authors Wang Wei, Harry Yang, Tiankai Yang, Samyadeep Basu, Hongjie Chen, Andy Zhao, Franck Dernoncourt, Ryan A. Rossi, Hoda Eldardiry
Computer Vision
Retargeting Motions to Diverse Skeletons via Learnable Flattening
Kia-Jüng Yang, Fabian H. Sinz and Paweł A. Pierzchlewicz
Cross-structural motion retargeting aims to transfer motion between different skeletal
topologies. Despite recent progress, existing state-of-the-art models struggle with reliability in zero-shot settings, i.e. skeletons with different
topologies which were unseen during training, and recent
Transformer-based attempts have failed to outperform specialized
geometric methods. We bridge this gap with a
Transformer Autoencoder that learns a
topology- and translation-invariant latent space. Our core contribution is a learnable flattening of skeletal graphs that captures both local dependencies and global structure. Unlike the standard
transformer architecture, which adds positional information to
token content, we integrate graph-based positional encodings multiplicatively, a design choice that follows directly from our flattening formulation. The resulting model handles diverse skeletal
topologies within a single unified architecture and trains in a fully unsupervised manner, requiring no paired retargeting data. Ablation studies show, that the graph encodings, multiplicative formulation, and
Transformer backbone is critical for the performance. In zero-shot evaluations, our method reduces global joint position error by $43-47\%$ over current
benchmarks. A user study ($n = 37$), including expert animators, further ranks our approach highest in motion
alignment and physical plausibility ($p < 0.05$). These results demonstrate that our model design is key to making
transformer architectures effective for motion retargeting, outperforming existing approaches.
Read the full abstract ▾
Artificial Intelligence
Conditional Generation of Creative Chess Puzzles with Diffusion Models
Aatu Selkee, Severi Rissanen, Xidong Feng et al. (+2 more)
While modern
language models demonstrate impressive generative capabilities, they often struggle with constrained, counter-intuitive creative tasks. To address this limitation, we explore chess puzzle generation as a rigorous testbed for computational creativity and
reasoning, a domain where altering a single piece can invalidate an entire solution. We propose a novel approach for conditional generation of creative chess puzzles using masked
diffusion models. Unlike previous methods, our non-directional
diffusion approach allows for conditioning on specific tactical themes and partial board positions. We introduce a novel auxiliary task of simultaneous best-move prediction, which improves solution uniqueness by 11.6% and theme-conditioning accuracy by 2.5%. To further optimize solution uniqueness and theme conditioning, we establish a reinforcement learning framework adapted from Denoising
Diffusion Policy Optimization (DDPO). This RL training increases the yield of unique and theme-matching positions by 89.1%. Finally, we release the first open-weights models (Appendix B) for chess puzzle generation, offering a new pathway for controllable, creative generation.
Read the full abstract ▾
All authors Aatu Selkee, Severi Rissanen, Xidong Feng, Tom Zahavy, Eric Malmi
Artificial Intelligence
Towards Model as a Library: Offline, Community-Sourced AI for Low-Resource African Languages
Fendji K. E. Jean Louis
Large
language models are frequently proposed as a route to AI-powered services for African communities, but they are least reliable exactly where the need is greatest: all African
languages remain low-resource by any standard measure, and models trained on scraped, standardised text systematically misrepresent the dialectal and regional variation of how people actually speak. We introduce Model as a Library (MaaL), a software architecture that packages small, community-enrolled
speech models as versioned on-device dependencies, enabling offline structured data collection that cannot generatively hallucinate, for populations that current
language models serve worst. Rather than relying on web-scraped corpora, MaaL's vocabulary is enrolled directly from a small number of example recordings by the speakers themselves, at the point of deployment. We describe the architecture and its central mechanism - keyword spotting that turns a closed-vocabulary text form into a voice form, filled and submitted entirely on-device - and propose transpiling the closed-vocabulary elements already present in widely-deployed digital form tools into MaaL schemas, a low-friction path to voice-first, offline data collection for the low-literacy populations these tools already reach. This is a position and system-design paper: we describe the concept, the mechanism, and an analytical feasibility case, and identify what a working implementation still requires.
Read the full abstract ▾
Computers and Society
Drowning in AI Slop: How Social Media Platforms (Do Not) Label AI and Deepfake Content under EU law
Bram Rijsbosch, Luka Bekavac, Henry Tari et al. (+2 more)
AI labels are emerging as a primary safeguard for transparency about AI-generated content on social media, including under the EU Digital Services Act and AI Act. Yet, limited systematic evidence exists on how platforms implement such labels in practice. We conduct a legally grounded audit of AI labelling across Instagram, TikTok, X, and YouTube, drawing on the European Commission's July 2026 guidelines on deepfakes. To this end, we analyse platform policies and detection approaches, 10,722 posts collected via systemic-risk and AI-related keywords, an expert-annotated subset of 500 posts, and controlled uploads to the four platforms of outputs from ten popular generative AI tools. We find that AI labelling is now broadly established. All four platforms apply labels automatically and a greater share of labels are platform-applied than in earlier audits. However, coverage remains incomplete where labelling arguably matters most: only 33% of expert-identified deepfakes in systemic risk contexts carried a platform-applied AI label, while reaching a median of 160,000 views. In controlled uploads of AI-generated content carrying standard AI provenance signals, platforms labelled only 61% of uploads, and commonly strip those signals after uploading. Overall, platform rules, label designs, detection approaches, and reporting diverge substantially. In response, we identify concrete opportunities to improve the uptake, clarity and efficacy of AI labelling.
Read the full abstract ▾
All authors Bram Rijsbosch, Luka Bekavac, Henry Tari, Gijs van Dijck, Konrad Kollnig
Robotics
Data-Efficient Adaptation of a Driving VLA to Class 8 Trucks
Satyajeet Das, Aaron Buxbaum, Niels Joubert et al. (+1 more)
Class 8 trucks differ from passenger cars in geometry, dynamics, and maneuvering requirements. As a result,
vision-
language-action (VLA) models trained for passenger vehicles do not readily transfer to Class 8 trucks, particularly in unstructured scenarios such as accident scenes and construction zones. Rather than training a truck-driving VLA from scratch, we propose an adapt-then-steer strategy that adapts an off-the-shelf VLA to generate trajectories for Class-8 trucks in these challenging scenarios. In the adapt stage, we use NVIDIA's Alpamayo 1.5 as the base model, fine-tuning only its action-generation stack on a few hundred real-world construction and accident-related highway scenarios. In the steer stage, we introduce Flow Velocity Steering (FVS) to further refine the model's predictions while holding the adapted VLA fixed. FVS is a compact, flow-time-conditioned residual module that adds learned corrections to the action-space flow velocity used to update the action sequence at each generation step. In open-loop evaluation on a scenario-disjoint held-out set, targeted fine-tuning more than halves single-candidate average displacement error (ADE) and final displacement error (FDE) over the entire 6.4 s horizon compared to the base model. Using the same targeted demonstrations, FVS further reduces the fine-tuned model's full-horizon ADE and FDE by 13.9% and 16.5%, respectively. At matched data budgets, targeted supervision yields 19-26% lower full-horizon ADE than general truck-driving supervision, while the targeted model remains competitive with a model fine-tuned on approximately 65 times as many general truck-driving scenarios. These results support adapt-then-steer for data-efficient vehicle-domain transfer to Class 8 trucks. Our project website is available at https://truckvla.github.io.
Read the full abstract ▾
All authors Satyajeet Das, Aaron Buxbaum, Niels Joubert, Gaurav S. Sukhatme
Machine Learning
The Advantages of Fresh Sketching for Ridge Regression
Linkai Ma, Qilin Li and Petros Drineas
Over the past 25 years, sketching and sampling have become widely used tools for accelerating large-scale regression. In iterative randomized solvers, a basic design choice is whether to $\textit{reuse}$ the same sketch or draw $\textit{fresh}$ randomness at every step. For (under-constrained) iterative ridge regression with column sampling, whether fresh sketches offer provable advantages has remained open: $\textit{We show that they do.}$ Fresh sketching lets us analyze error only along the current residual solution, rather than uniformly over the entire Gram
matrix. This directional view yields sharper convergence guarantees for leverage score and ridge leverage score sampling and, more importantly, leads to residual-aware sampling rules. By minimizing the variance of the relevant sketched
matrix-vector product, we derive an oracle distribution and practical approximations to the oracle distribution, including a mixture sampling distribution with (somewhat weaker) convergence guarantees. Experiments on synthetic and real data, including ridge probes on Qwen2.5 representations, support our theory, showing substantially faster convergence.
Read the full abstract ▾
Computers and Society
Navigating the Changing Landscape of Online Knowledge Consumption and Production in the Age of Generative AI: Evidence from Stack Overflow
Ji Eun Kim, Léa Vitale, Libby Hemphill et al. (+1 more)
Online knowledge communities rely on a division of epistemic labor between users who seek information and those who produce it. Generative AI may blur these roles, but how it reallocates knowledge-seeking and knowledge-producing activities and reshapes the nature and returns of participation remains unclear. We examine changes in question-asking and answering among Stack Overflow user groups, focusing on consumers and producers, following the release of ChatGPT. Consumers shifted from asking questions to producing answers, but their answers were less likely to be accepted relative to the pre-ChatGPT period, suggesting that increased production did not yield equal standing in the community. By contrast, producers did not change the number of questions they asked, but increasingly asked about novel and emerging topics. Although they produced fewer answers, their answers received greater recognition. These findings show that access to generative AI does not necessarily translate into equal opportunities for successful participation.
Read the full abstract ▾
All authors Ji Eun Kim, Léa Vitale, Libby Hemphill, Yulin Yu
Computer Vision
LongTake: Learning to Sustain Dynamics in Long-Horizon Video Generation
Byoungwoo Park, Jaemoo Choi, Juho Lee et al. (+1 more)
World models, game simulators, and long-take
video creation require coherent scene
evolution and sustained dynamics over extended durations. Autoregressive (AR)
video diffusion provides a natural framework for long-horizon generation, yet extended rollouts often become near-static or lose visual quality. We hypothesize that these failures reflect the limited guidance provided by short-
video supervision on how ongoing scene dynamics develops over longer durations. This motivates us to introduce LongTake, a two-stage training pipeline built around Long-Horizon Teacher Forcing (TF) on curated real long
videos. Long-Horizon TF trains the AR model to predict later frames conditioned on long ground-truth
video prefixes, extending direct supervision beyond the short training horizon. This supervision is designed to help the model sustain dynamics and preserve visual quality during long-horizon generation. Our central finding is that this training stage strengthens direct initialization for distribution matching
distillation (DMD) under student self-rollout, without the intermediate few-step
distillation stage used in standard pipelines. Under the same five-second DMD training setup, our initialization yields substantially higher dynamic degree than short horizon TF initialization on 30-second rollouts at comparable aesthetic quality, and surpasses the evaluated baselines in both measures. Hybrid DMD further reuses this teacher to extend supervision to later frames of the self-rollout while retaining bidirectional joint supervision over the initial window. On long-horizon self-rollouts, LongTake lies on the Pareto front of dynamic degree and aesthetic quality, and Hybrid DMD attains the highest dynamic degree among evaluated methods at both 30s and 60s.
Read the full abstract ▾
All authors Byoungwoo Park, Jaemoo Choi, Juho Lee, Yongxin Chen
Machine Learning · Cross-listed from math.OC
Parameter-Free Zeroth-Order Optimization with Ellipsoidal Sampling
Alexander Sholokhov and Alexander Rogozin
Zeroth-order optimization methods are essential for solving black-box problems where gradient information is unavailable or expensive to compute. This paper presents POEM-ES, a novel parameter-free
stochastic zeroth-order
algorithm that extends the recent POEM method by integrating subspace preconditioning with ellipsoidal randomized sampling. In contrast to traditional zeroth-order approaches that rely on isotropic random directions, POEM-ES performs anisotropic sampling guided by a fixed structural symmetric positive semi-definite (SPSD) preconditioner $\hat{\Sigma}$ that encodes the underlying low-dimensional geometry. Under a standard structural spectral normalization where $\lambda_{\max}(\hat{\Sigma}) = 1$, we introduce the use of the empirical effective dimension $d^* = \operatorname{tr}(\hat{\Sigma})$, which reflects the intrinsic dimensionality of the problem and guides both the sampling and randomized smoothing parameter schedules. In practice, such a preconditioner can be effectively obtained via pilot sampling, historical trajectories, or domain-specific expert knowledge. We prove that POEM-ES achieves a dimension-reduced convergence rate under low-rank structural assumptions, requiring only $\tilde{\mathcal{O}}\left( \frac{\left( r^2 \kappa(\hat{\Sigma}) + d^* \right) L^2 D_{\mathcal{X}}^2}{\varepsilon^2} \right)$
stochastic zeroth-order oracle queries. The method remains fully parameter-free and demonstrates significant improvements over the original POEM in problems with low-rank structure where $d^* \ll d$. Numerical experiments on hinge-loss binary classification tasks using LibSVM
datasets confirm the practical superiority of the proposed approach.
Read the full abstract ▾
Computer Vision
Detail in Context: A Dual-Scale Machine Learning Framework for Mycosis Fungoides Detection
Mohamed Hazem, Tarek Waleed, Omar Khaled et al. (+8 more)
Mycosis fungoides (MF) is a rare form of cutaneous T-
cell lymphoma that is often misdiagnosed in early stages due to its visual similarity to benign inflammatory dermatoses. Early and accurate diagnosis is critical for improving patient outcomes. In this paper, we propose a comprehensive diagnostic framework for automated MF detection that combines dual- scale histopathological image analysis with deep learning. To distinguish MF from other lymphoproliferative skin conditions, the proposed approach leverages a late-fusion ensemble of dual- magnification (10x and 20x) convolutional neural networks (CNNs), complemented by a random forest classifier trained on 16 clinical features. Experimental results on an expanded
dataset of 6,267 images (4,306 MF; 1,961 Non-MF) across 463 patients demonstrate that strong detection performance is obtained by prioritizing higher-resolution cytological details (20x) within broader architectural context (10x). The image-based late-fusion model achieves an accuracy of 83.58% and a sensitivity of 89.13%, while the clinical random forest model achieves an accuracy of 96.6% and sensitivity of 93.8%, highlighting the po- tential of this
multimodal framework as a robust clinical decision support system in dermatology. This framework addresses two distinct clinical objectives: an image-based dual-scale pipeline optimized for the early diagnostic screening of MF versus non- MF dermatoses, and a complementary clinical metadata model designed for the subsequent staging of confirmed MF cases (patch/plaque versus tumor)
Read the full abstract ▾
All authors Mohamed Hazem, Tarek Waleed, Omar Khaled, Nada Omar, Mahmoud Raslan, Marwa Mohamed Fawzy, Aya Fahim, Rania M. Mogawer, Ahmed Mourad, Kariman Mansour, Muhammad Rushdi
Artificial Intelligence
Defining and Categorising Human-AI Interactions in Clinical Trials: A Multidimensional Human-AI Classification Approach
Sandra Woolley, Tim Collins, Khalid Khattak et al. (+3 more)
This paper examines human-AI interactions (HAIIs) in clinical trials and presents a multidimensional categorisation framework that classifies interactions according to AI tasks, human-AI relationships, interaction configurations and interacting human groups. We define HAII, examine existing taxonomies and extend existing categorisation approaches through this novel multidimensional framework. We purposively sampled 15 clinical trials from a previously reported
dataset. Each trial was independently categorised by two human reviewers and six large
language model (LLM) classifiers. The proposed categorisation provides a structured method for the consistent identification, comparison and synthesis of human-AI interactions across clinical-trial records. The framework is intended to support more consistent comparison and synthesis of AI-related clinical trials and to make explicit the different forms of human involvement associated with AI interventions. The results demonstrate the potential for LLM-assisted categorisation while indicating the continuing importance of human judgement where trial records are incomplete or ambiguous. The principal contribution is a proposed multidimensional framework that brings together AI tasks, human-AI relationships, interaction configurations and interacting human groups within a single approach designed for clinical-trial records. Its significance lies in its potential to support more systematic identification, comparison and synthesis of how humans and AI interact in clinical trials.
Read the full abstract ▾
All authors Sandra Woolley, Tim Collins, Khalid Khattak, Illia Chernomorets, Ariane Arevalo, Chris Richardson
Artificial Intelligence
Demographic Pluralism: Inference-Time Modeling of Pluralistic Human Preference Distributions
Meng-Chen Wu, Qipin Chen, Ansh Jain et al. (+3 more)
Large
language models (LLMs) are increasingly used in culturally sensitive settings, where
alignment requires representing diverse preferences within populations. Yet existing methods model populations at coarse demographic or community levels and overlook within-group variation. We introduce Demographic Pluralism, an inference-time framework that estimates population-level opinion distributions without opinion-distribution training data or task-specific fine-tuning by generating multiple perspectives within demographically grounded groups. Across four backbones on GlobalOpinionQA and VITAL, it reduces Jensen-Shannon distance by 8.4%-26.4% over Modular Pluralism. Among weighted, equal-weighted, and inverse-weighted aggregation, equal weighting performs best overall; group-level error also increases with group weight, helping explain weighted aggregation's weaker performance.
Read the full abstract ▾
All authors Meng-Chen Wu, Qipin Chen, Ansh Jain, Tess Wood, Zhe Du, Si-Chi Chin