Computation and Language
Delta Tokenizer: Reference-Identical Tokenization of Session Deltas and Segment-Parallelism for Long Prompts on Multicore CPUs
Zhenyu Zhang and Zhichao Cao
An
agent that drives an LLM sends the model the same conversation again and again, and each turn adds only a little text at the end. Inference engines reuse the KV cache of the shared prefix, so only the new
tokens pass through the model. However, tokenization has no such shortcut. The CPU front end of the serving engine converts every request back into
token IDs from its first character, which lengthens the time to first
token (TTFT) and consumes CPU on every turn. We present Delta Tokenizer, a CPU tokenization front end that tokenizes only the delta between a request and the previous request of the same session. It retains the earlier
token sequence, encodes again only the appended text and the short tail whose
tokens the append could affect, and joins the two only at a position the tokenizer's splitting rules themselves cannot move, which keeps the result exact. For long requests with no state to reuse, it cuts the text where practical tokenizers already keep neighboring pieces independent, encodes the pieces on several cores at once, and concatenates the outputs into the reference encoding, exactly. A shared CPU pool schedules these chunks together with the short incremental updates, so an update runs between two chunks rather than behind an entire long job. The incremental path shortens the tokenization of a session turn by roughly 40x relative to the Hugging Face reference tokenizer, and on 16 cores the chunk-parallel path encodes a four-million-character request 8.2x faster than a serial encode and 1.6-2.1x faster than LoPT. Inside SGLang, Delta Tokenizer reduces the median TTFT through the chat interface by 59% at 100K
tokens and brings the P99 TTFT of
agent sessions down 9.5x under load and 23x when long requests tie up the front end. Every output we checked matches the reference, among them 41.8 billion documents encoded by its fast encoder.
Read the full abstract ▾
Computation and Language
Evolve Together, Fall into Place: How Social Scaffolding Shapes Self-Evolving Multi-Agent Systems
Seojin Hwang, Youngmin Choi and Hwanhee Lee
Recent work lets LLM
agents evolve their own harness, up to the team itself. Yet in human groups, the same abilities achieve different outcomes under different social conditions. Borrowing the notion of scaffolding from developmental psychology, we investigate whether the social scaffolding of a self-evolving multi-
agent system (MAS), namely its team composition and structure of interdependence (e.g., collaboration, conformity, or competition), shapes how the team evolves. We present AGORA (
Agents Growing through Organization and Relational Arrangements), a framework that varies the two axes independently across three
evolution mechanisms. Across web search, codebase understanding, and document QA, we find that (1)
evolution alone rarely helps, while the right scaffolding surpasses a strong
agent evolved alone by up to 25 points; (2) it does so by moving authority to the most capable member while the others step back; and (3) this member, having grown within the team, outperforms the same model alone. Designing a self-evolving MAS thus requires designing its social scaffolding, which shapes not only how its
agents learn, but who gets to lead.
Read the full abstract ▾
Robotics
Design and Characterization of a Unified Continuum Robot Actuation Platform
Yunti Xu, Aedan Mangan, Miheer Potdar et al. (+2 more)
Continuum
robots enable dexterous access to confined spaces in applications such as minimally invasive surgery and industrial inspection. However, their actuation systems are often custom-designed for specific
robot architectures and tasks, limiting reuse across publications, institutions, and applications. This paper presents a unified actuation platform that decouples actuation hardware and software from continuum
robot design. The platform provides modular actuation across continuum
robot classes, scales to a large number of degrees of freedom (DOFs), and integrates with conventional serial manipulators for hybrid architectures. We validate the platform on an open-sourced surgical robotic system and experimentally characterize the actuation modules, achieving sub-millimeter translational accuracy and less than $5^\circ$ rotational error over ranges of $30$~mm and $180^\circ$, respectively. We further demonstrate the platform in two surgical use cases: teleoperation of a continuum camera in a constrained environment and bimanual manipulation using $2.53$~mm concentric-tube-
robot-based forceps alongside a conventional wristed instrument. All hardware designs and ROS-based software are open-sourced to facilitate reuse and further research in continuum and surgical robotics.
Read the full abstract ▾
All authors Yunti Xu, Aedan Mangan, Miheer Potdar, Alex Lu, Tania K. Morimoto
Numerical Analysis
Smooth periodic extensions by extrapolation and blending for FFT-based differentiation
Ivan Méndez-Cruz and Faisal Amlani
Non-periodic functions on closed intervals are extended into sufficiently smooth periodic functions through a continuous Hermite interpolation framework with necessary and sufficient endpoint conditions, using smooth blend-to-zero operators and short extrapolation recurrences. A
matrix-free method is introduced for generating these smooth periodic extensions on the fly directly from function values at equidistant points. No precomputed continuation operator or auxiliary basis construction is required. The resulting extensions can then be used for FFT-based differentiation of non-periodic functions. Numerical tests are provided to show the effectiveness of the method, including for the highly accurate solution of a 1D linear advection equation.
Read the full abstract ▾
Artificial Intelligence
Learning Perception to Action Rules through Reinforcement Learning for Theory-of-Mind Reasoning
Soyoung Oh, Nursulu Sagimbayeva, Nicholas Jennings et al. (+3 more)
In Theory-of-Mind (ToM)
reasoning, large
language models may correctly infer the
agent's mental state but fail to use that inference when predicting or judging the
agent's subsequent actions. In this work, we investigate whether explicitly connecting perception, belief, and action with rules improves ToM
reasoning. We generate concise if–then rules that express relations between perception to action and use Group Relative Policy Optimization (GRPO) to train Qwen2.5 and Llama3 models across four ToM
benchmarks. GRPO with rule generation outperforms prompting, supervised fine-tuning, and think
reasoning. Moreover, rules generated by larger models ($\geq$3B) provide transferable knowledge that improves downstream performance of GPT-4o-mini. These findings suggest that explicit rules help models bridge the
reasoning gap in ToM and support knowledge transfer across models.
Read the full abstract ▾
All authors Soyoung Oh, Nursulu Sagimbayeva, Nicholas Jennings, Paulina Hussein, Mehwish Alam, Vera Demberg
Computer Vision
StateCraft: Augmenting Video World Models with Abstract-State Reasoning
Lorenzo Venturoli, Nedko Savov, Xi Wang et al. (+2 more)
Video world models aim to simulate complex environments with realistic appearance and dynamics. Maintaining consistency over long interactions requires tracking past actions and understanding how those actions affect the environment.
Video world models can only generate partial observations of the entire world at a time. Remembering past observations alone may not be sufficient in every scenario, as they may no longer reflect the world after a sequence of actions. We introduce a paradigm that decouples a persistent, updatable abstract state from the visual state. The abstract state keeps track of the entities' changes as the world evolves, and is used to condition the visual state, which represents the current view. We propose StateCraft, a novel architecture that pairs a
language model with a
video diffusion model to evolve the dynamic world. We evaluate our approach on generative interfaces, which pose a substantial challenge because a single action may change parts of the state that are not currently visible. To support training and evaluation, we develop a data collection pipeline that produces informative, densely annotated trajectories at scale without human or
agent supervision, together with a
benchmark measuring generation quality,
memory, and controllability. On this
benchmark, our approach improves surpasses the state-of-the-art baselines. We demonstrate that StateCraft maintains high self-consistency and strong generation quality over long trajectories. Because the abstract state is explicit, it can be edited directly, and generation follows edits to states never observed in the data. Finally, a proof-of-concept 3D experiment, in which actions change the illumination of an unobserved room, shows that the paradigm can also be applied to spatial environments. Project page: https://insait-institute.github.io/StateCraft/.
Read the full abstract ▾
All authors Lorenzo Venturoli, Nedko Savov, Xi Wang, Marc Pollefeys, Luc Van Gool
Computational Engineering
A posteriori error bounds for cumulative energy fields in irreversible gradient damage
Yubo Huang, Xiongyu Hu, Xin Lai et al. (+1 more)
Cumulative energy fields in irreversible
evolution depend on the loading path, even when terminal states and global work agree. We derive a posteriori bounds for these fields in scalar gradient damage with a prescribed driving density. A perturbation estimate for the incremental obstacle map yields a continuous loading history, which is enclosed by nondecreasing residual supersolutions. A primitive identity transfers this enclosure to the cumulative field. An exact endpoint-rule defect and outward arithmetic certify the output delivered by the numerical method. The analysis separates spatial, loading, and algebraic errors and gives sufficient conditions for certificate decay. Computable realizations use splines and verified supersolutions in one dimension and on two-dimensional rectangles. The production bounds cover the independently enclosed errors of all 417 saved histories from 28 adaptive calculations and all 25 fixed-parameter controls. In a narrow-localization case, the verified relative error decreases from approximately 158.78% to below 2.125% at a 5% certified target. Source-oriented marking reduces accumulated
matrix–vector work by 35.9% and 51.9% in two comparisons. A mechanically generated two-dimensional
benchmark shows how auxiliary supersolutions sharpen constant barriers and enable acceptance of both loading orders.
Read the full abstract ▾
All authors Yubo Huang, Xiongyu Hu, Xin Lai, Cheng Lyu
Computation and Language
JetSpec++: Foresight Parallel Drafting with Self Refinements
Zhaoxiang Feng, Lanxiang Hu, Haoran Yuan et al. (+6 more)
Speculative decoding's effectiveness is governed by two quantities: the acceptance rate of drafted
tokens and the cost of producing them. We show the two objectives can be co-optimized with
algorithm-system co-design, and present JetSpec++, which retains a strong learned draft model while hiding its cost almost entirely. JetSpec++ combines three components: intra-block self refinement, which trains the draft model to iteratively correct its own parallel predictions within a block of
tokens; inter-block foresight drafting, which begins the next block before the current one is verified; and pipelined drafting and verification, which overlaps the two stages so drafting's marginal wall-clock cost approaches zero. In comparison with state-of-the-art speculative decoding methods, JetSpec++ attains a wall-clock speedup of up to $7.45\times$ over autoregressive (AR) decoding and $1.54\times$ over DSpark, with up to 1,361
tokens per second for a single request on GB200, and an average acceptance length of 8.94 across seven
benchmarks, while preserving the target model's output distribution. Our code and models are available at https://github.com/hao-ai-lab/JetSpec.
Read the full abstract ▾
All authors Zhaoxiang Feng, Lanxiang Hu, Haoran Yuan, Yu-Yang Qian, Jihui Yang, Peng Zhao, Yibo Zhu, Tajana Rosing, Hao Zhang
Multiagent Systems
One Agent per Zone: Decentralised Active Inference under Partial Observability for Multi-Zone HVAC Control on Edge Hardware
Panagiotis Kasnesis, Lazaros Toumanidis, Christos Chatzigeorgiou et al. (+2 more)
Multi-zone HVAC control is a shared-resource problem: zones on a floor share one fan and cooling coil, so each zone's demand affects its neighbours and the building's peak power. One controller per zone scales well and isolates faults, but each controller then observes only its own zone, not the shared air loop. In this work, we present a decentralised controller that assigns each zone an independent active-inference
agent, which plans by minimising expected free energy and learns its zone dynamics online. The
agents exchange no messages, so none depends on peers or a coordinator; each accounts for the unobserved coupling through a latent disturbance and a congestion signal derived from the metered power of the other floors. Fifteen
agents are evaluated in EnergyPlus on a Sinergym office building against three rule-based controllers and three MADDPG fleets, one given the same floor meters. On five noisy weather years unseen during training, the fleet attains the lowest mean building peak (88.3 kW, 3 to 17 % below the baselines) and staggers the floor peaks better than any baseline, with a coincidence factor (building peak over the sum of the floor peaks) of 0.929 versus 0.936 to 0.994. Compared with a reactive rule at similar comfort (0.912 versus 0.916), it lowers the sum of monthly peaks, on which demand charges are billed, by 33 kW (4 %) in every year, at the cost of about 10 % more energy. It costs 9% less per year than the proactive rule (at lower comfort) and 1% less than the MADDPG fleet given the same floor meters, in every test year. The whole fleet runs on a single low-cost Raspberry Pi 5, closing the observation-to-action loop over MQTT in 442 ms at p95, far below the 15-minute control step.
Read the full abstract ▾
All authors Panagiotis Kasnesis, Lazaros Toumanidis, Christos Chatzigeorgiou, Amalia Contiero Syropoulou, Miguel De Prado
Computation and Language
More Methods, Better Agents? A Reality Check on Self-Distillation in Agentic Reinforcement Learning
Linhao Zhong, Bozhen Fang, Xuehao Wang et al. (+7 more)
Self-
distillation in agentic reinforcement learning has produced a growing number of methods. However, existing evaluations often reuse published baseline scores under differing experimental conditions, provide few direct comparisons among contemporaneous methods, and give limited
attention to training stability and computational cost. These limitations obscure the source of reported gains and the practical strengths and weaknesses of competing methods. Costly
agent training further motivates a common basis for comparison. To address these gaps, we compare ten representative methods against GRPO on ALFWorld, ScienceWorld, Search-QA, and WebShop across three model sizes. Our study comprises 132 training runs totaling 12,124.4 recorded H800 GPU-hours, with repeated evaluations over eight rollout seeds for the pretrained backbones and all eleven trained methods. Beyond final task performance, we examine training progress, stability, and measured computational cost. Our evaluation yields three key findings. First, gains over GRPO remain limited in scope, with no method consistently outperforming it across settings. Second, strong final performance can mask unstable training. Third, additional training cost does not consistently translate into better performance. We establish this
benchmark to support fair, comprehensive comparison and guide future research toward reliable and cost-effective improvements in
agent training. Project page: https://aim-uofa.github.io/Self-
Distillation-AgentRL/
Read the full abstract ▾
All authors Linhao Zhong, Bozhen Fang, Xuehao Wang, Duochao Shi, Zekai Luo, Guangming Yao, Yi Yuan, Hao Chen, Jingdong Chen, Chunhua Shen
Computer Vision
LiFi: LiDAR Generation from Multi-View Images via Geometric and Semantic Collaborative Guidance
Sizhuo Zhou, Xiaosong Jia, Fanrui Zhang et al. (+10 more)
Generating
LiDAR point clouds from multi-view camera images is a valuable task with applications in controllable data synthesis, cross-modal simulation and various perception tasks. However, most existing methods are not specifically designed for this task, and the quality of their generated
LiDAR remains limited. Moreover, these methods typically focus only on semantic cues in images or generate
LiDAR from a monocular camera image. In this work, we introduce LiFi (
LiDAR From images), a dedicated framework for generating visually and geometrically aligned
LiDAR scenes from multi-view camera images. LiFi guides the latent
diffusion process through two complementary branches: geometry and semantics. The geometry branch constructs scene features from images through a reverse sampling
algorithm and an uncertainty-aware
geometric encoder combined with DepthAnything3, whereas the semantic branch provides high-level semantic representations via a cross-view interaction module. We further introduce a dual-branch balanced classifier-free guidance (CFG) strategy, which enhances the model's conditional generation capability while preserving the independent learning and collaborative controllability of the two branches. Extensive experiments demonstrate that LiFi outperforms state-of-the-art methods in generating high-fidelity
LiDAR scenes. The code will be publicly available at: https://github.com/szzhou88/LiFi.
Read the full abstract ▾
All authors Sizhuo Zhou, Xiaosong Jia, Fanrui Zhang, Qifeng Li, Junjie Li, Zirui Wang, Yukang Feng, Yu Hong, Shaofeng Zhang, Wenlong Liao, Tao He, Juyong Zhang, Junchi Yan
Computer Vision
FPV-CRASH: A Dataset for Offline Crash Moment Localization in Drone First-Person-View Videos
Jifan Zhang, Tingyu Wang, Qian Liu et al. (+1 more)
Crash Moment Localization aims to localize the major physical impact that interrupts controlled flight in an onboard first-person-view (FPV)
video recorded by a drone, thereby providing a temporal reference for retrospective crash analysis in aerial robotics. However, existing crash-
video datasets predominantly target surveillance or dash-camera footage, and their annotation schemes and task formulations are not designed for temporal localization of the major physical impact in
UAV onboard FPV
videos. To address this gap, we present FPV-CRASH, a
dataset and fixed-protocol reference evaluation for offline Crash Moment Localization in drone FPV
videos. FPV-CRASH contains 1,052 drone FPV clips (526 Crash and 526 Normal); each Crash clip has a single-frame reference annotation for the Crash Moment, and every clip is paired with four English captions automatically generated from sampled frames and the known Crash/Normal label. Normal clips carry no timestamp target and provide training-time background supervision. The captions support an auxiliary Text-to-
Video Retrieval task, whereas localization inference remains
video-only. We further provide a heatmap-based reference model that estimates a continuous Crash Moment timestamp from sparsely sampled frames. Under the fixed, non-source-disjoint clip-level protocol, the reference model reduces MAE from 1.12 s for the strongest fixed timing-prior baseline to 0.56 s (a 50% relative reduction) and achieves a median absolute error (MedAE) of 0.33 s; the fraction of clips localized within 0.5 s rises from 37.14% to 65.71%. The release includes annotations, available source
video identifiers and URLs, clipping metadata, fixed split lists, and preprocessing code so that the reportable portion can be reconstructed without redistributing source footage. At submission time, all source-compilation URLs remained accessible.
Read the full abstract ▾
All authors Jifan Zhang, Tingyu Wang, Qian Liu, Zhedong Zheng
Information Theory
Joint Identification, Transmission, and Sensing over State-Dependent Channels with Noiseless Feedback
Vida Gholamian, Marcel A. Mross, Roberto Ferrara et al. (+2 more)
We consider a discrete memoryless state-dependent channel with noiseless feedback, where the transmitter uses randomized encoding to jointly perform message transmission, identification, and state sensing. In this setting, the transmitter sends a conventional transmission message and an identification message while estimating the unknown channel state sequence under an average distortion constraint. We establish a single-letter characterization of the randomized identification-transmission-sensing capacity-distortion region. The result reveals a single-letter separation structure: the communication rates are determined by the averaged channel, subject to the sensing-induced constraint on admissible input distributions. Specifically, the transmission rate is characterized by mutual information, while the identification rate is characterized by output
entropy under the same distortion constraint. The achievability proof combines constant-composition transmission coding, output partitioning, and combinatorial identification coding, while the converse follows from an averaged-channel reduction, distortion lower bounds, and feedback-identification converse arguments.
Read the full abstract ▾
All authors Vida Gholamian, Marcel A. Mross, Roberto Ferrara, Eduard A. Jorswieck, Christian Deppe
Machine Learning
Reinforcement Learning via Advantage Guidance
Zhiyuan Zhou and Sergey Levine
Reinforcement learning (RL) holds the promise of learning a policy that can outperform what is shown in the data. However, in practice, such systems suffer from instability and hyperparameter sensitivity. In contrast, supervised learning provides a stable and scalable training objective, but is fundamentally limited by the quality of the demonstrated behavior. In this paper, we ask whether we can perform policy optimization with something as simple and stable as supervised learning but as performant as RL. Unfortunately, naively training the policy with supervised learning and conditioning on future rewards or advantages typically underperform dedicated RL methods. We introduce a new policy extraction method, Advantage Guidance, that retains the simple supervised learning structure with advantage conditioning while outperforming prior RL methods through effective conditional training and contrastive
diffusion guidance during sampling. We show that Advantage Guidance can significantly improve a model's ability to respond to conditional advantage signals, and the contrastive guidance during sampling can use the learned advantage-conditioned policy to target the KL-regularized optimal policy. Empirically, we find that Advantage Guidance significantly outperforms prior state-of-the-art RL methods on 26 long-horizon, sparse reward tasks across
datasets with varying degrees of optimality.
Read the full abstract ▾
Machine Learning
Learning Who Benefits Most: Multi-Treatment Causal Ranking for Population Health Stratification
Rocco Zaccagnino, Martina Girolamo, Alberto Lombardi et al. (+3 more)
Population health stratification frameworks, such as the Italian DM77, organize patients by clinical need and care pathways but offer limited guidance on which care changes to prioritize under constrained resources. We present PROMETHEUS (Proactive Resource Optimization through Multi-treatment Effect-based Targeting in Healthcare Environments Using Stratification), a framework that formulates population health stratification as a multi-treatment causal ranking problem. Its objective is to order eligible patient-treatment opportunities by expected incremental benefit rather than obtain perfectly calibrated individual treatment-effect estimates. Each clinically admissible care intensification is compared with maintaining the patient's current pathway. Treatments are learned jointly to produce a globally comparable ranking across patients and care profiles, within domains sharing a reference condition, outcome, follow-up horizon, and benefit scale. This separates clinical need, treatment benefit, and resource-constrained allocation. PROMETHEUS combines doubly robust causal signals with a Siamese neural ranking model and contrastive representation pretraining. The shared representation captures similarities across care transitions, supporting prioritization under capacity constraints. Synthetic experiments and semi-synthetic experiments using real administrative
covariates from ASL Benevento evaluate ranking quality, allocation value, robustness, and failure modes. The results support the framework's ability to recover generated benefit orderings and prioritize care opportunities in the evaluated settings. PROMETHEUS provides a preclinical approach to actionable stratification; validation with observed treatment-outcome data is required before clinical use.
Read the full abstract ▾
All authors Rocco Zaccagnino, Martina Girolamo, Alberto Lombardi, Delfina Malandrino, Donatello Telesca, Alessia Ture
Machine Learning · Cross-listed from stat.ML
SNACK: A Sequential Notation Framework for Probabilistic Graph Generation
Hohyun Kim, Hyesung Kim, Min-hwan Oh et al. (+1 more)
We introduce SNACK, a string representation for probabilistic graph generation that enables sequence models to generate and model graphs with discrete node and edge features. SNACK linearizes graphs by encoding the nonzero entries of the lower-triangular adjacency
matrix, establishing a bijective correspondence between valid sequences and ordered adjacency
matrices. This design enables invalid logit masking to enforce structural constraints–such as chemical valence and ordering rules–guaranteeing 100% valid generated sequences. SNACK also enables principled string-based GFlowNet training by explicitly accounting for node-ordering
symmetries. Across standard graph-generation tasks and molecular distribution-learning
benchmarks, SNACK achieves competitive sample quality, while substantially improving the throughput of GFlowNet training relative to graph-based generation. Probing analyses further show that models trained on SNACK encode meaningful local and global graph structure despite receiving only sequential supervision. These results position SNACK as a practical framework for probabilistic graph generation with deep sequence models.
Read the full abstract ▾
All authors Hohyun Kim, Hyesung Kim, Min-hwan Oh, Seunggeun Lee
Artificial Intelligence
LabOPBench: A Multimodal Benchmark for Evidence-Grounded Laboratory Decision Making
Jingyuan Li, Yujie Liu, Yijie Dai et al. (+18 more)
Laboratory experiments involve more than following predefined protocols; they require adaptive decision-making as the experimental state changes. Existing scientific
benchmarks rarely assess such evidence-based decisions in laboratory settings. Here we present LabOPBench, a
multimodal benchmark of 756 expert-authored, independently reviewed questions in organic synthesis and materials science. Each item pairs laboratory evidence with procedural context and an open-ended judgment, evaluated using a question-specific scoring rubric. Eight
multimodal models obtain overall normalized scores of 28.8-45.8%, leaving substantial room for improvement. On a controlled 100-question subset, the strongest models outperform undergraduate participants on average but remain below the average performance of PhD participants. Expert analysis of responses from the three leading models identifies Evidence Misreading and Evidence-Decision Conflict as the dominant error patterns. These results reveal that current models still struggle to turn
multimodal perception into reliable laboratory decision-making.
Read the full abstract ▾
All authors Jingyuan Li, Yujie Liu, Yijie Dai, Xiaoyu Yuan, Nian Ran, Huajie Niu, Ming Zhu, Shuwen Zhao, Chenxi Li, Fenghao Lu, Jiahao Li, Xinyu Gu, Zhe Liu, Long Xu, Wenlong Zhang, Bo Zhang, Lei Bai, Peiyu Zhang, Minting Pan, Weinan Zhang, Dongzhan Zhou
Computer Vision · Cross-listed from physics.optics
Computational compressive imaging reconstruction with a simulated-annealing-based Ising solver
Ze Zheng, Xiaoyan Wu, Hang Xu et al. (+3 more)
Computational compressive imaging, such as single-pixel imaging and lensless imaging, is a promising imaging technique, enabling the reconstruction of objects from under-sampled measurements through compressed sensing
algorithms or deep learning methods. However, the demand for electronic computational resources grows rapidly when recovering high-resolution and multi-dimensional images and training neural networks with numerous parameters, which has become a bottleneck for the widespread adoption of this technique. Here, we propose a physics-driven reconstruction framework that formulates imaging inverse problems as Ising models and directly recovers target objects through the self-
evolution of non-von Neumann Ising machines toward the ground state of the
Hamiltonian. We employ a simulated-annealing-based Ising solver to demonstrate this proof-of-concept by reconstructing objects in both single-pixel imaging and a lensless diffuser camera at sampling rates ranging from 1% to 25%. By further incorporating a foreground-sparsity constraint and a smoothness constraint, the reconstruction quality of our method is comparable to or even better than that of mainstream
algorithms. This approach has the potential to substantially reduce the electronic computational burden of inverse reconstruction, paving the way for real-time, low-power computational imaging.
Read the full abstract ▾
All authors Ze Zheng, Xiaoyan Wu, Hang Xu, Jingzheng Huang, Tailong Xiao, Guihua Zeng
Computer Vision
Q-MAGIC: Quad-only Mesh Autoregressive Generation via Singularity-Aware Circular Relative Offset Tokenization
Yuming Zhao, Zezeng Li, Weimin Wang et al. (+2 more)
Autoregressive models have proven effective for triangular mesh generation by transforming it into predicting the next face, converting the non-differentiable connectivity prediction into a sequence of
token predictions. However, generating quad-only meshes remains challenging because quad faces impose stricter topological constraints than triangles. The model must not only serialize quad faces into a valid
token sequence, but also support unambiguous connectivity reconstruction during de-serialization. To address this, we propose Q-MAGIC, a novel autoregressive model for quad mesh generation. We first introduce a tailored serialization scheme for quad meshes, which requires at least two new vertices for the next face and is less flexible than triangles due to strict wiring constraints. To meet these requirements and reduce serialization length, we propose a singularity-aware serialization that prioritizes wiring from singular points, leading to more coherent traversals. Additionally, we propose a circular relative offset tokenization that encodes geometry mainly via local relative offsets. Built upon this representation, an autoregressive
Transformer learns the underlying distribution of quad meshes via next-
token prediction, enabling effective quad mesh generation. Extensive experiments demonstrate that Q-MAGIC produces more compact sequences while consistently improving
geometric fidelity and mesh quality compared to state-of-the-art methods.
Read the full abstract ▾
All authors Yuming Zhao, Zezeng Li, Weimin Wang, Xiang Wu, Na Lei
Sound
Long-Prompt Zero-Shot TTS: Benchmarking Prosody Reproduction Beyond Voice Cloning
Dekun Chen, Renjie Xu, Yingda Shen et al. (+2 more)
Zero-shot text-to-
speech (TTS) typically conditions on a short
speech prompt, which conveys timbre but provides only limited evidence of a speaker's prosodic patterns. We formulate Long-
Prompt Zero-Shot TTS, a task that uses long
speech prompts at inference time to reproduce speaker-specific prosody without target-speaker fine-tuning. We introduce LP-TTS-Bench, a bilingual
benchmark of 37 speakers with 63.95
prompt hours and 2,728 held-out test utterances. Beyond intelligibility and timbre similarity, LP-TTS-Bench evaluates timing, prominence, intonation, and model-based prosody metrics, enabling multidimensional evaluation of prosody reproduction. As a reference system, we develop LPTTS, whose hierarchical Long-
Prompt Encoder compresses long
speech prompts into a fixed number of continuous prosody vectors. Experiments show improvements in several prosodic dimensions over a short-
prompt baseline, with overall gains as
prompt duration increases up to approximately 10 minutes and saturation at longer durations.
Read the full abstract ▾
All authors Dekun Chen, Renjie Xu, Yingda Shen, Qinke Ni, Zhizheng Wu
Machine Learning
From Global to Tail Convergence: Dynamics of $\alpha$-Stable Score-Based Generative Models
Ianis Hammani and Claire Boyer
Score-based generative models driven by $\alpha$-stable Lévy processes have been proposed as an alternative to Brownian
diffusion models, with empirical evidence suggesting improved sampling and better modeling of heavy-tailed data. Yet theoretical guarantees for these models remain limited. We develop a non-asymptotic convergence analysis for scale-preserving $\alpha$-stable generative dynamics, covering both compactly supported and power-law targets. In p-Wasserstein distance, we quantify the effects of early stopping, initialization, score approximation, and time discretization, and show exponential decay of the initialization error. A comparison with Brownian dynamics reveals that global Wasserstein convergence alone does not fundamentally distinguish the two models: both initialization errors decay exponentially with the forward horizon on the common class of heavy-tailed targets. A sharp separation emerges instead in the tails. At any positive generation time, stable dynamics produces power-law tails with index $\alpha$, whereas Brownian dynamics remains light-tailed. For a target with tail index $\nu$, asymptotically correct extreme-
quantile scaling is possible precisely when $\alpha$=$\nu$. These results identify tail-index matching as a principled mechanism behind the ability of stable generative models to capture extreme events.
Read the full abstract ▾
Software Engineering
When Does the Dependency Graph Help Code-to-Architecture Mapping?
Rakhshanda Jabeen, Morgan Ericsson, Jonas Nordqvist et al. (+1 more)
Architectural technical debt arises when a system's implementation drifts from its inten ded modular decomposition, while the mapping between source files and architectural modu les is missing, incomplete, or costly to maintain manually. We formulate code-to-archite cture mapping as semi-supervised node classification over a directed multi-relational de pendency graph, with files as nodes, typed dependencies as edges, and lexical features d erived from code identifiers and directory layout. Starting from a small labeled sample, an iterative self-training procedure expands the mapping to the remaining files. We com pare a graph convolutional network (GCN), a graph
attention network (GAT), and a graph-f ree multi-layer perceptron (MLP), using identical features and training procedures for t he learned models, against a Naive Bayes reference. Across 100 runs on ten open-source J ava and C/C++ systems, all three neural models outperform the reference on both F1 metri cs. GAT achieves the highest averages of system-level median macro and micro F1, at 83.5 and 92.2, respectively, whereas MLP remains competitive or superior on several systems. On Chrome, the largest system with 18,343 files, GAT and GCN exceed MLP by 22 and 19 ma cro-F1 points, respectively, and have substantially fewer persistently misclassified fil es. Connectivity and homophily are associated with where neural message passing helps, w hile multi-relational aggregation outperforms a single merged edge type on every system for both GCN and GAT. A follow-up study finds that several model rankings depend on the training seed, qualifying smaller advantages without removing the large graph benefit ob served on Chrome.
Read the full abstract ▾
All authors Rakhshanda Jabeen, Morgan Ericsson, Jonas Nordqvist, Anna Wingkvist
Machine Learning
Learning to Compute Is Not Learning to Retain or Reuse in Looped Transformers
Peilong Zhou, Hongtao Zhang, Yulong Huang et al. (+3 more)
Looped
transformers compute by applying one block repeatedly, so they can run for more loops than they were trained with. Recurrent reasoners are known to overthink: iterating past the trained depth can turn a correct answer into a wrong one. Such a late error can reflect failed computation, loss of retention, or a state that later computation cannot reuse. We separate these cases in in-context Mealy-machine execution, where a simulator supplies intermediate targets and exact counterfactuals for hidden-state interventions. Models trained to answer at loop 32 are fully correct there but keep only 22% of these answers at loop 64. Retention depends on what training asks for: supervising one randomly chosen position per example, instead of always the last, keeps 99.8%, and randomizing the number of training loops also helps; truncating gradients, as in progressive training against overthinking, does not. The computation itself is exact: position $k$ is computed at loop $k$, and swapping its loop-$k$ hidden vector for the one from another input redirects every later position to that input's exact continuation (237/237 pairs in each of ten models). Retention, however, is not reuse. Even in models that keep nearly all answers, holding each position $k$ fixed from loop $k$ drops accuracy to 4–6%, whereas holding it from loop $k+4$ is harmless. A released recurrent maze network trained to avoid overthinking behaves the same way. Learning to compute is thus not learning to retain, and avoiding overthinking does not make a state reusable when its answer first appears.
Read the full abstract ▾
All authors Peilong Zhou, Hongtao Zhang, Yulong Huang, Cangyuan Li, Mingyu Chen, Ying Wang
Computation and Language
Likelihood Is Not Authorship: Can We Reliably Measure Human Contribution in AI-Assisted Writing?
Hasan Amin, Zhuoran Lu and Ming Yin
AI-text detection generally asks whether a machine wrote a text. As AI becomes an increasingly integral and accepted part of writing, the more relevant question is no longer whether AI was used, but how much of the text reflects human contribution. A prominent line of work estimates this by measuring how predictive a person's
prompt is of the final text. We show that this measure can be easily manipulated. We introduce SPECIFICITY PADDING that simply asks the model to copy a few random IDs from the
prompt, and that alone makes a title-only request look more human than one that supplies the article's key ideas. A context-swap audit then holds each document fixed, and only shows or hides the IDs to the evaluator. The score of the unchanged text swings by a third to half of its scale, and it rises for every document we test, on news and scientific abstracts, across varied LLMs from 3.8B to 753B parameters. The same articles can average 85% human or 15% human depending only on which
prompt is on record, and even with no
prompt at all, the output-only variant rewards the random strings themselves. An exact identity, the credit ledger, explains why. The score is a surprisal-weighted average over the text, so rare strings that the context makes copyable collect the credit, whatever they mean. A two-point bound marks a deeper limit. If the
prompt could have been machine-written, every transcript-only method must, in the worst case, miss by half the contribution at stake. Likelihood-based scores alone cannot reliably establish human contribution without evidence of what the person added and how the text was produced.
Read the full abstract ▾
Cryptography and Security
Analyzing and Mitigating Poisoning Attacks on Flow-Based Intrusion Detection
Florian Spelter, Johannes F. Loevenich, Tobias Hürten et al. (+4 more)
Although Artificial Intelligence (AI)-based Intrusion Detection Systems (IDSs) are increasingly deployed in operational networks, their dependence on large-scale training data introduces a critical vulnerability to stealthy poisoning attacks. We demonstrate that latent backdoors can be successfully implanted in flow-based IDS models by poisoning as little as 0.001% of the training data, maintaining near-nominal performance on clean inputs while ensuring high attack success rates. To address this threat, we propose a diagnostic-first methodology that localizes trigger-relevant features through constrained perturbation analysis and detects poisoning-induced behavioral drift by comparison with a distilled baseline model. The proposed methodology further enables targeted mitigation via automated data sanitization or
neuron pruning. Our findings expose the operational risks of near-undetectable backdoors and provide a scalable approach to analyzing, quantifying, and mitigating backdoor exposure in AI-based IDS.
Read the full abstract ▾
All authors Florian Spelter, Johannes F. Loevenich, Tobias Hürten, Erik Adler, Maxime Schwarzer, Laurin Holz, Roberto Rigolin F. Lopes
Robotics
Refine Actions If Needed: Adaptive Action Chunk Refinement for Robot Manipulation
Hanlin Liu, Zichen Zhou, Jiacheng Zhang et al. (+6 more)
Computationally lightweight manipulation policies predict executable actions with low inference latency, but prediction errors can limit task success. Iterative generative policies can achieve higher task success rates, but repeated network evaluations increase inference latency. Refining action proposals from computationally lightweight policies can combine these strengths, but the amount of refinement needed varies across states. We introduce RAIN (Refine Actions If Needed), a framework that predicts action errors at different refinement levels to decide whether and how much to refine each executable proposal, before performing any refinement. We train an ensemble to predict these errors by comparing action proposals and their refined versions with expert actions from offline demonstrations, without requiring explicit labels of refinement needs. Calibration balances uncertainty, computation, and temporal consistency. We evaluate RAIN on eight ManiSkill tasks and four real-
robot tasks. In simulation, our policy achieves 66.6% success, approaching the best evaluated
diffusion-policy success rate with 5.71 times lower policy latency. On the real
robot, success increases from 55.0% with Action Chunking with
Transformers (ACT) to 72.5%, with comparable average successful completion time. Matched controls show that dynamic routing maintains the strongest observed fixed-refinement success level with 26.6% fewer refiner evaluations. Project page: https://rain-policy.github.io/.
Read the full abstract ▾
All authors Hanlin Liu, Zichen Zhou, Jiacheng Zhang, Liuyuan Na, Jin Jin, Guangyan Chen, Yufeng Yue, Gen Li, Fangqiang Ding
Programming Languages
Verifying deployed bytecode against executable EVM semantics, with exact gas and no added axioms
Seulkee Baek
Much of Ethereum's most consequential code is immutable bytecode: old output of unverified compilers, and protocol logic run as contract code. We show that such bytecode can be verified as it is, without trusting what produced it, without simplifying the machine it runs on, and with no axioms beyond Lean's own. Blanc, a Lean 4 verification stack, reads fixed runtime bytes via kernel-checked certificates and states every
theorem against Jaune, an executable semantics of the EVM and block processing that passes all 34,205 blockchain-test cases of Ethereum's fixture release v20.0.2 that involve only forks that have governed mainnet since May 2025. Eight artifacts, deployed from 2017 to 2026, come from seven compiler versions and an assembler. For the EIP-7002 contract, we prove that the end-of-block call to it, whose failure would invalidate the block, succeeds whatever its storage holds, and that each block's withdrawal requests are exactly the oldest pending submissions; mainnet met these
theorems' starting premises when Prague began. For a Uniswap V2 pair, we prove that after any valid history whose hashed slots stay apart, from any checkpoint representing its Solidity model's state, the storage represents that model replayed over exactly the committed calls, a balanced liquidity ledger stays balanced, and, under a premise on
token answers,
geometric-mean reserves per share fall only through the protocol fee. Exact gas makes liveness provable: a tracked WETH9 holder without code can withdraw by a transaction whose gas has a closed form, matching all 3,748 comparable mainnet receipts of its shape in 30,000 blocks. On Curve pool bytes compiled with the lock bug exploited in 2023, Jaune executes such a reentrancy from deployment; for bytes from a fixed compiler, we prove the lock excludes it. AI
agents wrote the proofs in fifteen days under one author's direction, atop an existing stack.
Read the full abstract ▾
Computer Vision
Physics-Shaped, Not Physical: Auditing Physics-Guided Underwater Image Restoration
Mochamad Rizal Fauzan and Irgi Surya
Physics-guided networks for underwater image restoration predict transmission and backscatter and invert the image-formation model, yet rarely test whether this physics does any work. We audit one representative design, PhysGuide-Net, with four controlled experiments: five-seed ablations on UIEB with zero-shot evaluation on the complete LSUI (4279 pairs) and AUIED3K (3000 pairs) sets; a data-efficiency study with a capacity-matched control that removes the formation model; and a validation of the predicted maps against measured range on Sea-thru. With all 800 training images the physics module gives no zero-shot gain (mean PSNR differences of at most 0.16 dB; all 95% intervals include zero) at 3.4x the FLOPs. With 80 images it helps more (+0.65 dB on UIEB, +1.48 dB on AUIED3K; seed-to-seed s.d. on AUIED3K from 1.3 to 0.5 dB), although not individually significant after correction, and the control does not reproduce this (0.8-1.0 dB lower). Yet the predicted transmission does not behave like a physical quantity: its correlation with range is no stronger than for the range map of a different image (pooled difference +0.02, versus -0.06 for the dark-channel prior), and a Beer-Lambert fit explains 0.4% of its variance. The effect of the module also changes sign with degradation severity between
datasets. The benefit thus comes from a physics-shaped inductive bias, not from physics. We further show that single-run ablations can reverse sign and document implementation defects that invalidate loss ablations.
Read the full abstract ▾
Computation and Language
PRISMATIC : Prescription Risk Inspection System for Multi-Agent Treatment Interaction in Clinical Decision-Making
Ziyang Ling, Shuyu Lu and Ziyi Chen
Medical prescribing errors for multimorbid patients, who require complex drug regimens, are a major patient safety concern. These errors often stem from fragmented decision-making across medical specialties, a critical coordination failure that leads to adverse drug events and rehospitalizations. To address this coordination challenge, we introduce PRISMATIC, a multi-
agent architecture where specialized
agents, each representing a workflow role, collaboratively generate and refine treatment plans. Operating on a blackboard architecture, the system first structures patient information from clinical notes, then iteratively develops safe, rational, and interpretable drug regimens. The
agents' collaboration is governed by two novel adaptive coordination mechanisms: (1) Dynamic Self-Updating Weight Adjustment (DSWA), a long-term mechanism that adjusts the influence weights of
agents based on historical case outcomes, enabling the system to adapt and trust more reliable specialists over time. (2) Discrepancy Feedback Precise Calibration (DFPC), a short-term mechanism where
agents provide iterative feedback to resolve disagreements and eliminate prescription conflicts for the current patient. Experiments on patient records from the MIMIC-IV database show that PRISMATIC significantly reduces drug conflicts, improves prescription coverage, and enhances treatment consistency compared to strong LLM baselines. Our work demonstrates that structuring clinical co-treatment as a multi-
agent coordination problem offers a promising path toward safer and more coherent multidisease management.
Read the full abstract ▾
Machine Learning
CAST: History-Adaptive Spectral Clipping for LLM Pretraining
Jiacheng Li, Jianchao Tan, Kefeng Zhang et al. (+2 more)
Soft spectral clipping (SSC) reduces gradient singular values, but its effect depends on the gradient scale and clipping threshold. We introduce CAST (Clipping with Adaptive Scales and Thresholds), a history-adaptive extension of SSC. AdamW's previous second moment sets row and column scales. An exponential moving average of the clipped output's estimated spectral norm sets each
matrix's threshold. CAST restores the original coordinates before the AdamW update. We train a mixture-of-experts (MoE) model with 19.08B total parameters for 83.89B
tokens. CAST achieves lower training and mean validation losses than nine gradient-processing baselines, with the fewest relative gradient spikes. It reaches the best baseline's final smoothed training loss in 7.2% fewer steps.
Read the full abstract ▾
All authors Jiacheng Li, Jianchao Tan, Kefeng Zhang, Yuchen Xie, Xunliang Cai