Numerical Analysis
Monte Carlo pricing under fast mean-reverting stochastic volatility: the multi-scale limit ${\epsilon\to 0}$
Laurent Mertz and Olivier Pironneau
We compute $\E[(S_T-K)^+]$ by Monte Carlo for a scalar
stochastic-
volatility model with a fast mean-reverting factor of time scale $\eps$, for $\eps$ ranging from $1$ down to $10^{-3}$. A conditional (mixing)
estimator gives finite variance, whereas the direct
estimator has infinite variance for this model. The
volatility factor is simulated with its exact Ornstein–Uhlenbeck transition. As $\eps\to0$ the price converges, at rate $O(\eps)$, to the Black–Scholes price with the averaged
volatility $\bar\sigma$, and the implied-
volatility smile flattens to $\bar\sigma$. Finally, we test a martingale control variate built on the Black–Scholes delta with
volatility $\bar\sigma$. If the martingale is driven by the true
volatility $\sigma(Y_t)$, the variance is reduced by a factor that grows like $1/\eps$, about $160$ at $\eps=10^{-3}$. If it is driven by the constant $\bar\sigma$, the variance is essentially not reduced. Last, we calibrate the model with $\rho\neq0$ to S&P~500 implied
volatilities by full simulation of $S$. At the same number of paths the control variate reduces the variance by a factor $1.7$–$16$ (median $5.6$) and gives more accurate calibrated parameters; at equal CPU time it pays off only if the delta is rebalanced on a coarser grid than the time step. For a basket of four indices (state dimension $8$) the gain is larger (median $8$) and the relative cost smaller, so that the control variate is about $4$–$5$ times more efficient than plain Monte Carlo at equal CPU time.
Read the full abstract ▾
Machine Learning
AnchorMixGAN: Anchor-Aligned Generative Semi-Supervision for DDoS Detection in Cloud-Integrated IoT Networks
Jin Yang, Xufeng Liu, Yong Hu et al. (+3 more)
Detecting distributed denial-of-service (DDoS) attacks in cloud-integrated IoT networks is difficult when labeled traffic is scarce. Generative semi-supervised learning can supplement the available training data, but prediction shifts induced by synthetic views may affect the targets assigned to real unlabeled flows. We propose AnchorMixGAN, a generative semi-supervised framework that addresses this problem through anchor-aligned target construction. Its Anchor-MAS module treats each real unlabeled flow as an anchor and creates alternative views by replacing one field group at a time with values from generated traffic. A frozen reference classifier predicts the anchor and its views; averaging and sharpening these predictions produces a soft target for the original flow. The flow and its target are then mixed with a labeled example using MixUp, allowing the detector to learn from both the original labeled records and the mixed examples. We analyze how reference-classifier error, view construction, and sharpening affect the target, and derive a bound on the resulting change in cross-
entropy at a fixed detector prediction. At the reported 90% training setting with 20% of the training records labeled, AnchorMixGAN attains accuracies of 97.3%, 97.4%, and 96.5% on NSLKDD, BoT-IoT, and CICIoT2023, respectively, exceeding the corresponding MixGAN results by 1.6, 1.0, and 4.4 percentage points.
Read the full abstract ▾
All authors Jin Yang, Xufeng Liu, Yong Hu, Xueyang Wang, Honglu Yang, Gang Li
Artificial Intelligence
Mandela-Bench: Multimodal Models Remember Canonical Images Instead of Seeing Them
Yicheng Bao, Zhenkun Gao, Xiahui Guo et al. (+7 more)
Historical photographs and other canonical images can now be edited seamlessly with a single instruction, often leaving no reliable pixel-level trace. In such cases, the only evidence of manipulation may be a fact about what the image depicts. Existing
benchmarks instead rely on generator artefacts, image-caption inconsistencies, visual implausibilities, or external references, and therefore do not test whether a model can use its own world knowledge to verify a recognized image. We introduce Mandela-Bench, containing 1,507 edits of canonical images: 1,359 knowledge-only forgeries, each contradicting one verifiable fact, and 148 anchor-free controls that preserve the editing process without introducing a factual contradiction, together with 474 untouched originals. We score not only whether a model detects a forgery, but whether its explanation identifies the inserted entity or the fact being violated. Across 36
multimodal models, from 0.8B parameters to frontier scale, we find a consistent failure mode. When a public figure is removed from a familiar photograph, models still name that person in up to 72.7% of responses. Some models can distinguish the replacement face from the original when shown in isolation, yet still judge the full edited photograph as authentic. Providing the true event and date does not improve knowledge-grounded detection, whereas providing the same information after cropping away the recognizable composition does. Even under explicit verification
prompts, only one of the 36 models meets the KGR criterion on at least half of the forged images. These results suggest that the failures cannot be explained by missing knowledge or inadequate perception alone. Instead, they are consistent with recognition biasing verification toward the remembered canonical image rather than the observed edit.
Read the full abstract ▾
All authors Yicheng Bao, Zhenkun Gao, Xiahui Guo, Mingqian Yang, Xueheng Li, Bangwei Liu, Mingang Chen, Lijun Li, Xuhong Wang, Xin Tan
Robotics
An Empirical Study on What Matters for Viewpoint-Generalizable Policies in Visual Imitation Learning
Mino Nakura, Sriram Krishna, Yufei Wang et al. (+3 more)
Visual imitation learning is a promising approach to training
robot manipulation policies capable of completing a wide variety of tasks. However, policies today remain brittle to viewpoint perturbations, making deployment in diverse environments a challenge. We present a controlled empirical study of which design choices allow visuomotor policies to generalize across viewpoints. We find that viewpoint generalization improves when dense visual
tokens are retained and the action head participates in
geometric reasoning. On a suite of simulated tasks that span a wide range of camera poses, we show that these design choices yield a policy that remains performant across viewpoints. As a practical consequence, a policy trained with these design choices also transfers zero-shot from simulation to the real world under random camera configurations.
Read the full abstract ▾
All authors Mino Nakura, Sriram Krishna, Yufei Wang, Shubham Tulsiani, Zackory Erickson, David Held
Computer Vision
From Feed-Forward to Flow: Unifying Reconstruction and Generation Is Easier Than You Think
Haoru Wang, Qianfan Shen, Kai Ye et al. (+2 more)
Reconstruct where the images provide evidence, and generate where they do not: recent success of spatial world models such as Atlas (World Labs Team, 2026) highlights the value of unifying reconstruction and generation in one model. Yet the two have long lived in separate paradigms with distinctive failure modes: feed-forward reconstruction averages ambiguity into blur, while conditional generation invents plausible but scene-inconsistent detail. In this work, we present a unified flow-based formulation for reconstruction and generation, where a shared clean-target predictor performs direct reconstruction at its single-step endpoint and unfolds conditional generation through multi-step flow. A controlled toy study reveals the mechanism: with a single step, the predictor collapses to the conditional mean just like feed-forward methods, favoring consistency over diversity. With multi-step inference, the fidelity of generated details grows with context richness: closer observations reduce ambiguity and yield better-matched details. We further instantiate the formulation in appearance and geometry 3D tasks. JiT-LVSM improves perceptual and distributional quality in novel view synthesis, while JUSt3R retains competitive single-step geometry prediction with additional multi-step inference capabilities that reduces veil and flying-pixel artifacts, producing cleaner surface structure with greater test-time compute. Together, they show that reconstruction and generation can share both a formulation and a backbone, with their behavior governed by denoising configuration—making unification surprisingly simple.
Read the full abstract ▾
All authors Haoru Wang, Qianfan Shen, Kai Ye, Wenzheng Chen, Baoquan Chen
Machine Learning
The Extender: A Log-Structured Transformer
Jakob Eriksson
We introduce the Extender, a log-structured variant of the standard
Transformer architecture. In a standard
Transformer, each layer communicates with subsequent layers exclusively via the residual $\mathbf{h}$, a superposition channel. The Extender adds a concatenation channel $\mathbf{x}$: each layer $\ell$ emits both a residual update $\delta_\ell$ which is added to $\mathbf{h}$, and a much smaller extension $\epsilon_\ell$ which is appended to $\mathbf{x}$. While both the FFN and $\mathbf{q}$ see $\mathbf{h}$, the
attention $\mathbf{kv}$ projections take only $\mathbf{x}$ as input. As a result, the fully extended $\mathbf{x}$ contains the complete input for the $\mathbf{kv}$ projections of all layers, reducing the persistent
attention memory footprint from $2Ld_{model}$ to $\sum|\epsilon_\ell|$. We find that with $|\epsilon_\ell|=32$, the Extender matches
Transformer accuracy on short-context (CORE) tasks at 199M-924M parameters, and exceeds
Transformer accuracy on long-context (RULER) workloads, again at 924M parameters. For our 1664-wide, 924M model, the Extender's persistent
attention memory footprint is $104\times$ smaller than MHA. The
memory savings grow with model width.
Read the full abstract ▾
Computation and Language
How Far Do Persona Effects Generalize in Language Models?
Yufan Zhou, Yuxuan Liu, Enze Ma et al. (+6 more)
Persona
prompts ask
language models to answer as particular kinds of people. We test whether relationships learned from these effects predict responses to new questions and remain useful across models and
prompts. Across 57 attributes, three behavioral domains, and seven pairs of open 7 to 9B checkpoints, persona effects can be predictable without being portable. Separate attribute and task gains improve prediction beyond shared scaling significantly in OLMo-3 and Qwen2.5, with the most robust evidence in OLMo-3. In that model, target refitting significantly outperforms gains borrowed from each of the other six pairs. Across model transfers, borrowed gains with one amplitude underperform shared scaling in most directions; allowing two target parameters removes the significant losses but yields no significant benefit over target shared scaling. After rewording, refitting significantly outperforms reuse with one amplitude in all six tested pairs, while changes of examples or country context often preserve reuse value. In the tested
prompt transfers, regularized updates outperform both reuse strategies in median at 64 target questions per attribute. A separate survey comparison finds that selecting the more responsive checkpoint can worsen human fit; responsiveness is confounded with training status, and temperature calibration largely removes this cost but not errors in group ordering. Within the tested gain representation, apparent transfer can come from target calibration; source relationships must add predictive value beyond calibration and regularization. Code and data are available at https://github.com/thzva/persona-gain
Read the full abstract ▾
All authors Yufan Zhou, Yuxuan Liu, Enze Ma, Lyumanshan Ye, Zhongqi Yue, Robin De Croon, Yucheng Jin, Katrien Verbert, Zhao Wang
Artificial Intelligence
Readout is not Recovery: Dissociating Coordinate Emission from Visual-Corruption Repair in Vision-Language Models
Drandreb Earl Juanico
VLM bounding-box localization is both
language generation and spatial commitment. Parseable fields such as bbox_2d make localization easy to score, but dimensions that emit coordinate
tokens need not repair localization after visual evidence is damaged. We study this readout/recovery separation in Qwen3-VL-4B-Instruct on single-object COCO grounding. We compare clean coordinate-
token readout rankings with corruption-derived repair rankings, using object-mask endpoint replacement for recovery and clean-input flooring for depth localization. In Qwen3-VL, coordinate-
token rankings are inert through layer 24, load-bearing from layers 32-35, and peak at layer 34; corruption-derived rankings harm layers 16-24 but become beneficial near layer 35/final. A Kimi-VL-A3B diagnostic shows a matching output-proximal transition despite a different box format. Object-mask recovery separates rank budgets: $k=250$ shows necessity, $k=500$ shows Top-$k$ restoration above random, and $k=d/2$ is largely capacity-driven. Partial-occlusion sweeps reveal that high-overlap coordinate-
token sets can hurt at $k=1000$ and help mainly at half-width, while population corruption-derived sets provide no reliable fixed repair set. Edge-attribution patching shows coordinate-
token paths are high precision but low recall for detection recovery, and RMSNorm quasi-layer controls do not close the endpoint-repair gap. Endpoint coordinate triage is therefore a useful
circuit prior, but occlusion recovery requires a separate
benchmark.
Read the full abstract ▾
Machine Learning
Reuse or Relearn? A Spectral View of Earth Observation Foundation Models
Mehmet Ozgur Turkoglu, Valerio Marsocci, Dominik J. Mühlematter et al. (+3 more)
Foundation models are rarely used as generic, frozen feature extractors; instead, they are fine-tuned for the target downstream application. This practice is particularly prevalent in Earth observation (EO), and it raises a question that downstream accuracy alone cannot answer: does fine-tuning reuse the pretrained representation, or does it relearn a new one? We study this with spectral diagnostics that compare a model before and after adaptation, quantifying how well its dominant singular subspaces are preserved, how broadly the weight update is distributed, and how large it is. Using natural image models such as CLIP and DINO as a reference, we find that, under the evaluated fine-tuning settings, EO models undergo far larger, higher-rank updates and retain much less of their pretrained structure, so their downstream performance is often obtained with substantial changes to the pretrained weight structure. The diagnostics further provide insight into how cheaply a model can be adapted: where the pretrained subspaces are preserved, adapting a small fraction of the parameters can match full fine-tuning, and where they are not, it can fall behind. More broadly, foundation models, and EO foundation models in particular, should be assessed not only by
benchmark accuracy, but also by how reusable their pretrained representation is.
Read the full abstract ▾
All authors Mehmet Ozgur Turkoglu, Valerio Marsocci, Dominik J. Mühlematter, Dominik Senti, Konrad Schindler, Helge Aasen
Sound
SAGE: Semantic Audio Generative Encoder
Francesco Brigante, Luca Cerovaz, Davide Marincione et al. (+4 more)
Audio autoencoders compress waveforms into compact latent representations that serve as the interface between raw audio and downstream models. Current systems navigate a three-way trade-off between reconstruction quality, semantic structure of the latent space, and inference speed, typically favoring one or two of these at the expense of the others. This paper introduces SAGE, Semantic Audio Generative Encoder: a compact variational autoencoder, trained solely on publicly available music, that shapes its latent by distilling
embeddings from a pretrained audio-text model. This 105M-parameter model runs about 3x faster than Stable Audio Open and reaches the listening-test quality of SAME-L, an autoencoder 8x larger and over 2x slower, while surpassing both on objective perceptual and distributional metrics of reconstruction. Furthermore, it sets the state of the art on all nineteen probing tasks of latent semantics, in domain and out of domain. These results establish SAGE as a lightweight audio autoencoder that strikes the best balance of the three-way trade-off among those we evaluate, combining high reconstruction fidelity, state-of-the-art semantic structure, and fast inference.
Read the full abstract ▾
All authors Francesco Brigante, Luca Cerovaz, Davide Marincione, Giorgio Strano, Luca Zhou, Emanuele Rodolà, Michele Mancusi
Artificial Intelligence
Adaptive Consistency Graph for Long-Horizon Agents
Jiecong Wang, Hao Peng and Zhanyi Wang
Large
language model
agents can often make reasonable local decisions on short tasks, yet their performance degrades when success requires long sequences of dependent actions and tool calls. During execution, task requirements, historical evidence, and the current execution state may gradually become disconnected, so later decisions can drift from the original objective. We study this problem by introducing the Adaptive Consistency Graph (ACG) for long-horizon execution. ACG incrementally organizes execution evidence and its provenance in a persistent graph, then constructs a temporary requirement-centered view for each decision under a bounded context budget. Rather than replacing the base
agent's planner or tool executor, ACG provides a structured and traceable context view for each decision. In the matched evaluation, ACG improves GPT-5.6-luna's average success from 44.5% with ReAct to 50.2%, with the largest gain on BrowseComp-Plus (73.5% versus 62.4%). We further analyze trajectory structure and inference cost to characterize this improvement. Our code is available at https://github.com/yunsaijc/Adaptive-Consistency-Graph.
Read the full abstract ▾
Artificial Intelligence
Action Shaping: Policies Absorb What They Can Express
Yanjun Chen, Jinghan Wang, Xiaoyu Shen et al. (+2 more)
Reward shaping has a
theorem: a potential-based term can be removed without changing the optimal policy. The same practice on the action channel, an offset added in training and dropped at deployment, has no
theorem. Nothing cancels an action offset, so the correction is kept at deployment or removed without a guarantee. We call it action shaping and state its principle. A trainable policy absorbs an offset its own output layer can reproduce exactly, which is what we mean by express; what is absorbed can be removed with the return intact. Its minimal instance is a zero-initialized linear head behind a learnable gate, added to an actor that trains through a learned action-value function, with no penalty or schedule. The gate rises and then falls on its own, for deterministic and
stochastic actors alike, and on 20 tasks removing the head costs almost nothing. The condition is exact reproduction, not capacity: a nonlinear head with more parameters is not absorbed, and in a paired control, one linear path added to a nonlinear base head restores absorption. Exact reproduction gives the loss a flat direction that gradient noise drifts along, and the offset's amplitude indicates, before removal, what dropping the head will cost. Action shaping thus gains the counterpart of the shaping
theorem, a condition for absorption, together with the mechanism behind it and a diagnostic that reads it. Policies absorb what they can express, and only that.
Read the full abstract ▾
All authors Yanjun Chen, Jinghan Wang, Xiaoyu Shen, Wenjie Li, Wei Zhang
Artificial Intelligence
CUA-Sandbox: Efficient Environments for Computer-Use Agent Reinforcement Learning
Xin Yan, Zhengbo Jiao, Jiaqi Liu et al. (+11 more)
Reinforcement learning enables computer-use
agents to improve through interaction with real software environments, including websites and desktop applications. However, conventional deployments replicate an initialized runtime for each independent rollout, even when trajectories use the same software, incurring repeated
memory and initialization costs as the number of parallel environments grows. Does an independent computer-use environment require an independent execution runtime? Our key observation is that trajectories require independent mutable state, while initialized application runtimes can be reused across concurrently evolving environments, making state the natural unit of environment independence. Guided by this observation, we introduce CUA-Sandbox, which separates private state capsules from shared runtimes through state-scoped execution and transactional lifecycle operations, including resets and branches, while retaining the original software interfaces and task evaluators. Experiments show comparable or improved task success relative to Docker, while substantially reducing rollout and resource costs. CUA-Sandbox achieves up to a 6.20x increase in rollout throughput, a 9.2x reduction in per-environment
memory, and a 504x reduction in incremental storage.
Read the full abstract ▾
All authors Xin Yan, Zhengbo Jiao, Jiaqi Liu, Zhenglin Wan, SiYuan Ma, Xuliang Yu, Tianyi Jiang, Chubin Zhang, Pengfei Zhou, Wangbo Zhao, Xingrui Yu, Bo An, Yang You, Ivor Tsang
Artificial Intelligence
Retrospective Distillation Attribution via Normalized Response Similarity
Minwoo Jang, Jaechang Kim, Minhyeon Oh et al. (+2 more)
Model
distillation transfers capabilities through supervised fine-tuning (SFT) on teacher responses, often collected from commercial APIs, raising questions of model provenance. Existing
distillation attribution methods have been largely evaluated on students immediately after the SFT step. However, a distilled model may undergo further SFT, preference optimization, or reinforcement learning before release, while an auditor may lack access to the pre-
distillation checkpoint required by reference-based attribution. To close this gap, we propose SCOUT, an output-only method that aggregates recurring *syntactic patterns* into candidate profiles, filters low-contrast patterns, and calibrates student–candidate distances against inter-candidate distances. SCOUT supports attribution and abstention using only current texts, without model weights,
token likelihoods, or historical checkpoints.
Auditing publicly released descendants of distilled models spanning diverse post-training objectives, SCOUT consistently identifies the
distillation source. Furthermore, tracing teacher-associated *syntactic signatures* along training trajectories reveals that they emerge during
distillation and persist through subsequent preference optimization and reinforcement learning.
Read the full abstract ▾
All authors Minwoo Jang, Jaechang Kim, Minhyeon Oh, Jeongyeon Hwang, Jungseul Ok
Systems and Control
Path Invariance of a Quadrotor System under Cyber Attacks with Theoretical Guarantees
Hamza Mahmood, Usman Ali and Adeel Akhtar
This paper presents a path-following controller for a quadrotor system to guarantee safe maneuvers, in terms of forward path invariance, in the presence of cyber-physical attacks. We assume that an
adversarial agent can control any one of the rotors through a false data injection (FDI) type of attack. A feedback controller is designed using transverse feedback linearization which guarantees that the system follows a class of smooth curves under FDI attacks. Our proposed controller is computationally efficient, with a closed-form analytical expression, that not only mitigates the effect of bounded malicious signal but also ensures mission success. We provide theoretical guarantees of forward path invariance under FDI attacks with realistic assumptions and demonstrate the effectiveness of our approach through simulation.
Read the full abstract ▾
Multiagent Systems
Self-Evolving Multi-Agent Symbolic Discovery for Financial Fundamental Analysis
Kelvin J.L. Koa, Filip Orestav, Shengqiong Wu et al. (+2 more)
While symbolic regression (SR) has been successfully used in science to discover new equations, its use in financial valuation is hindered by several limitations. Whereas the natural sciences provide objectively correct relationships, financial valuation constitutes a distinct class of symbolic discovery problems, as it admits multiple valid perspectives, operates under non-stationary
market conditions, and involves noisy, continuous performance signals. In this work, we propose Multi-
Agent Fundamental Analysis with Symbolic Adaptive learning (MUFASA), a hierarchical multi-
agent framework for symbolic discovery in finance. MUFASA introduces (1) disentangled equation discovery via specialized
agents representing distinct valuation perspectives, (2) a meta-coordinator that performs hierarchical-level
reasoning over
market context information, and (3) a
memory mechanism that reasons over statistical performance summaries (e.g., accuracy, stability, and tail risk) to guide learning under noisy feedback. Experiments across
datasets from multiple countries show that MUFASA achieves state-of-the-art performance on the valuation task compared to classical finance methods, financial large
language models, and SR approaches, while simultaneously producing interpretable equations, which we share with the community. We also make publicly available the distilled learnings across
evolution iterations and context-dependent strategy weights, which might offer useful insights for future research on financial fundamental analysis.
Read the full abstract ▾
All authors Kelvin J.L. Koa, Filip Orestav, Shengqiong Wu, Michael J. Wooldridge, Ke-Wei Huang
Robotics
MORPH: Self-Organising Multi-Robot Task Allocation via Neuroplasticity-Inspired Adaptive Topology
Xuezhi Niu and Didem Gürdür Broo
Multi-
robot task allocation (MRTA) in dynamic environments faces a fundamental tension: effective coordination requires learned structure, but that structure must adapt when conditions change. Existing methods resolve this by assuming prior task knowledge, a utility function, a cost
matrix, or a trained policy making them brittle when deployed without such knowledge or when task distributions shift. We present MORPH(Multi-
agent Online Rewiring through Plasticity-guided Hierarchy), a training-free MRTA framework where global allocation quality emerges from 4 local plasticity rules (synaptic, homeostatic, structural, and metaplasticity) applied to a directed pairwise preference
matrix updated from runtime co-occurrence and task-completion feedback. MORPH requires no task model, no bid computation, and no offline training; response decisions use learned AGV-to-Picker preferences rather than a fixed proximity rule. Within the Gerkey-Mataric MRTA taxonomy, MORPH is the first method in the single-task, single-
robot, instantaneous-assignment class to learn directed pairwise allocation preferences online. Evaluated on the TA-RWARE warehouse
benchmark (8-24
agents, 4 maps, 800 steps per episode, 5 seeds), MORPH achieves 110% of all-to-all throughput at N=24 while using only 21% of possible coordination links as an efficiency advantage that grows monotonically with fleet size. Under spatial task distribution shift, MORPH degrades 3x less than proximity-based methods while its learned preferences remain uncorrelated with Manhattan distance. Systematic ablation confirms all four plasticity rules contribute measurably. Two allocation properties emerge without programming: cross-type preference dominance and progressive preference sparsification, mirroring the developmental refinement of biological neural
circuits. Learned preferences are driven by task co-occurrence history, not spatial proximity.
Read the full abstract ▾
Machine Learning
Benchmarking EEG Foundation Models at Scale: Lessons from 20,000 Evaluations
Zhige Chen, Shu Peng, Chengxuan Qin et al. (+4 more)
Electroencephalography (
EEG) foundation models (FMs) promise transferable neural representations, yet their advantages over strong supervised baselines and their prospects for further scaling remain unclear. To address these questions, we introduce
EEG-Arena, an open-source
benchmark covering 30
EEG FMs and 25 supervised baselines evaluated on 57 downstream tasks from 23 public
datasets. Through more than 20,000 evaluations across five experimental protocols, we assess downstream performance, pretraining benefits, model size scaling, pretraining data scaling, and robustness to channel configuration. We find that (1)
EEG FMs outperform strong task-specific supervised baselines on most evaluated tasks, particularly under non-bipolar settings; (2) compared with architecture-matched supervised training from scratch, pretraining improves both early optimization and final downstream performance, with larger and more consistent gains as more labeled downstream data become available; (3) existing
EEG FMs do not exhibit a consistent positive relationship between parameter count and downstream performance; (4) under a fixed architecture, increasing the pretraining data scale yields sustained downstream gains; and (5) channel-flexible FMs achieve higher absolute performance than channel-constrained models across most evaluated channel configurations. Together, these findings demonstrate the downstream value of
EEG FMs and identify pretraining data expansion as a promising direction for further progress. To support continued research, we release
EEG-Arena as an open-source evaluation framework that provides shared infrastructure for reproducible benchmarking, model comparison, and community-driven development.
Read the full abstract ▾
All authors Zhige Chen, Shu Peng, Chengxuan Qin, Rui Liu, Rui Yang, Kay Chen Tan, Jibin Wu
Computer Vision
LoCoVSR: Local Context Diffusion Posterior Sampling for Video Super-Resolution
Matan Ben Chorin and Michael Elad
Video super-resolution (VSR) is an ill-posed inverse problem that aims to reconstruct a high-resolution (HR)
video from a noisy, low-resolution (LR) version of it. We present LoCoVSR, a
diffusion-based VSR framework that leverages pixel-space denoising
diffusion probabilistic models. LoCoVSR integrates the
Diffusion Posterior Sampling technique with spatio-temporal context learning, operating in a moving-average form. A localized window of adjacent LR frames is used for recovering each center frame, while applying a shared noise trajectory across all frames. The localized windowing enables processing of long
videos without length limitations, supports parallel inference, and prevents error accumulation that may occur in recursive processing. Unlike prior methods, LoCoVSR offers a simple yet very effective VSR solution, avoiding explicit optical flow estimation, or information loss caused by latent space processing. Trained on the VFHQ face
dataset, LoCoVSR achieves accurate, temporally consistent and high-quality upscaling with competitive results against recent
diffusion-based VSR approaches.
Read the full abstract ▾
Machine Learning
Predicting the Financial Impact of Supply Chain Risk for Major AI-Related Semiconductor Firms: A Heterogeneous Graph Patch Transformer Approach
Jianna Hur and Sagar Samtani
Modern
semiconductor production relies on a globally distributed, multi-tier supply chain in which financial stress at one firm spreads with a delay and eventually affects the revenue, inventory, and profitability of the companies that design AI chips. Most firms see only their direct partners, and prior predictive research has mainly targeted
market-based risk measures, so few tools forecast how supply chain stress will appear in reported financials. In this study, we propose a heterogeneous graph patch
transformer that forecasts these quarterly changes one and two quarters ahead. Learning from a 15,186-company network over 60 quarters, the proposed model fuses quarterly fundamentals with macro-trade, event, and disaster signals through learned gates, carries risk across supplier, customer, ownership, and headquarters relations through typed, direction-specific propagation, and encodes the propagated histories with patch-based tokenization. In preliminary experiments on 116 focal
semiconductor firms, the proposed model achieves the lowest error on every target at both horizons, and its profitability advantage widens at the two-quarter horizon. These forecasts can help supply chain managers and investors act before disruptions appear in reported financials.
Read the full abstract ▾
Computer Vision
AnesTRACE: Benchmarking Intraoperative Anesthesia from Multimodal Perception to Multi-step Decision-Making
Ziwei Huang, Qi Gao, Zhe Ji et al. (+5 more)
Intraoperative anesthesia requires systems to interpret evolving
multimodal evidence, recommend timely management, and revise decisions as patient states change, yet existing
benchmarks usually isolate perception or single-point
reasoning. We introduce AnesTRACE, an evaluation suite comprising AnesTRACE-Bench and AnesTRACE-Eval. Built from public perioperative
datasets with anesthesiologist annotation, AnesTRACE-Bench evaluates Intraoperative Perception, Single-point Anesthesia Decision-Making, and Multi-step Anesthesia Decision-Making. AnesTRACE-Eval assesses open-ended responses through anesthesiologist-defined criteria for Clinical Correctness, Evidence Grounding, Task Completeness, and Safety, with Temporal Consistency for multi-step decisions; its domain-specific evaluator is trained by supervised fine-tuning and preference
alignment on expert-reviewed judgments. Across more than 30 models, fine-grained visual grounding and intervention selection remain difficult: the leading model reaches only 32.2 mIoU for TEE visual grounding and retains a 17.5% Major/Critical Safety Error Rate in multi-step management. Evaluator
alignment with anesthesiologists improves across both training stages, while the best decision quality is accompanied by a 74.3-second P95 Latency. These results show that aggregate performance alone does not establish safe, timely longitudinal decision-making. We release our code at https://zjudbxai.github.io/AnesTRACE/.
Read the full abstract ▾
All authors Ziwei Huang, Qi Gao, Zhe Ji, Yuanyuan Yao, Fengjiang Zhang, Min Yan, Zhongle Xie, Gang Chen
Human-Computer Interaction
Chatbot Engagement Does Not Always Beget Metalearning: Evidence from Three Countries
Kokil Jaidka, Insyirah Binte Imam Mujtahid, Peng Qi et al. (+5 more)
Chatbots deliver real-time fact-checks, but whether a chatbot correction leaves anything behind once the chatbot is gone - metalearning, distinct from correcting misbeliefs - is untested. We report a preregistered, three-country randomized experiment (USA, India, Singapore; N ~ 2,200) on out-of-context image misinformation, manipulating a correction's channel affordances (synchronicity, bandwidth) across four conditions: Control, Links-only, Static explanation, and a Socratic Chatbot built on a validated out-of-context detector, with an unaided retest one week later. The Chatbot produced the largest immediate discernment gain (d = 0.097, p = .023). All three interventions reduced sharing of false claims (d ~ -0.12, p < .01). One week later, no advantage persisted: the Chatbot arm declined relative to Control, most sharply in India and Singapore, and in India on claims it never discussed. Decay tracked affordance level and did not vary by country. Engagement mechanisms, we argue, do not substitute for slow AI literacy.
Read the full abstract ▾
All authors Kokil Jaidka, Insyirah Binte Imam Mujtahid, Peng Qi, Harshit Aneja, Subhayan Mukerjee, Wynne Hsu, Mong Li Lee, Tsuhan Chen
Computer Vision
Gradient-Guided Decoupled Adaptation for Geospatial Vision-Language Models
Dongdong Wang, Deepak Balakrishnan, Ravi Srinivasan et al. (+1 more)
Existing geospatial
vision-
language models (Geo-VLMs) typically optimize diverse geospatial tasks through a unified multi-task adaptation paradigm without explicitly accounting for the heterogeneous optimization characteristics. Our empirical observations reveal heterogeneous gradient characteristics across tasks, including
vision-
language differences, intra-branch gradient relationships, and task interference, which hinder effective multi-task optimization. Motivated by these observations, we propose Gradient-Guided Decoupled Adaptation (G2DA), a gradient-aware optimization framework for multi-task Geo-VLM learning. G2DA first partitions tasks into
vision- and
language-centric groups through gradient-guided cross-modal decoupling. It then constructs modality-specific curricula based on task gradient similarity and employs bidirectional rehearsal to mitigate the recency effects introduced by sequential optimization. We evaluate G2DA on three Geo-VLM
benchmarks using six InternVL3 and Qwen3.5-VL variants, along with GeoChat and GeoLLaVA. Across all 24
benchmark-model combinations, G2DA consistently outperforms representative baselines, improving over the strongest competitor by 3.08, 4.30, and 2.81 percentage points on UrBench-MCQ, XLRS-Bench-Lite, and VRS-Bench-VQA, respectively. These results demonstrate the effectiveness of gradient-guided task organization for Geo-VLM adaptation.
Read the full abstract ▾
All authors Dongdong Wang, Deepak Balakrishnan, Ravi Srinivasan, Shenhao Wang
Data Structures and Algorithms
Near-Optimal Distributed Domination in Planar Graphs
Wojciech Wawrzyniak
We give a deterministic $(8+\varepsilon)$-approximation for minimum dominating set on planar graphs in a constant number of rounds of the LOCAL model, for every $\varepsilon>0$. This improves the previous ratio $11+\varepsilon$ obtained by Heydt et al. The ratio is near-optimal in this model: its leading constant is only one above the known lower bound of $7$. Our result closes three quarters of the previous gap, reducing it from $4$ to $1$. Our main contribution is a sharp structural bound. For any dominating set $D$, assigning each vertex outside $D$ to a neighboring center gives disjoint owner blocks. If $k_x$ counts the other blocks containing a neighbor of $x$, then $\sum_{x\notin D}(k_x-2)^+\le(4|D|-12)^+$, where $z^+=\max\{z,0\}$. The bound holds for every such assignment, and equality holds for arbitrarily large minimum dominating sets. We use this bound in their three-phase framework, with new parameters and the same final linear-programming procedure. The
algorithm requires neither a planar
embedding nor the graph size, and its round bound depends only on $\varepsilon$. The transfer
theorem of Bonamy et al. also gives a deterministic $(25+\varepsilon)$-approximation on graphs of bounded Euler genus, with a round bound depending only on $\varepsilon$ and the genus.
Read the full abstract ▾
Systems and Control
Characterization and Monitoring of Nonlinear Dynamics and Chaos in Complex Physiological Systems
Hui Yang, Yun Chen and Fabio Leonelli
Nonlinear dynamics arise whenever multifarious entities of a system cooperate, compete, or interfere. For example, cardiovascular system involves a great level of complexity. Multi-lead ECG signals are generated through orchestrated depolarization and repolarization of
cells and manifest significant nonlinear dynamics. Nonlinear dynamical systems defy understanding based on the traditional reductionist's approach, in which one attempts to understand a system's behavior by combining all constituent parts that have been analyzed separately. In order to cope with system complexity, modern healthcare systems are investing in advanced physiological sensing and patient monitoring, thereby giving rise to big data. Realizing the full potential of big data for healthcare intelligence requires fundamentally new methodologies to harness and exploit complexity. However, available nonlinear dynamics techniques are either not concerned with healthcare analytical objectives or fail to effectively analyze big data to extract useful information for improving healthcare services. There is an urgent need to develop analytical methodologies that fully exploit the underlying nonlinear dynamics in physiological systems for advancing healthcare services with exceptional features such as personalization, responsiveness, and superior quality. This chapter presents some theoretical developments and tools to advance the applications of nonlinear dynamics principles in health care. Specifically, we focus on sensor-based characterization and modeling of nonlinear dynamics (i.e., multifractal analysis and multiscale recurrence quantification). Then, current developments and applications of these methodologies are examined for characterizing and exploiting heart rate variability and space-time ECG signals.
Read the full abstract ▾
Computer Vision
REALIS: A Curated Dataset for Studying the Challenges of AI Image Detection
Aleksandr Gushchin, Khaled Abud, Georgii Bychkov et al. (+5 more)
AI-generated image detectors are often evaluated on
benchmarks where real and synthetic images differ in content, quality, or generation artifacts, allowing models to rely on
dataset-specific cues and fail on unfamiliar generators or processed images. Existing
datasets provide limited support for evaluating these challenges jointly across diverse visual content. We introduce REALIS, a
dataset of 1.43 million real and synthetic images generated by 42 modern text-to-image models, including the latest proprietary systems such as Nano Banana 2. REALIS combines
prompts derived from real images, quality filtering, and stratified sampling to reduce class-specific shortcuts while preserving content diversity. We further introduce REALIS-Expert, a stress-test subset for high-quality synthetic images, where real and generated samples are selected with closely matched semantic and visual characteristics. We also propose a robustness protocol covering 35 transformations at five severity levels to analyze detector behavior under image processing. Based on REALIS, our
benchmark evaluates pretrained detectors, fine-tuned models, and zero-shot
vision-
language models under generator and post-processing shifts. On the hardest processed split, the best pretrained conventional detector achieves 0.550 ROC-AUC, compared with 0.752 for the best REALIS-trained detector. REALIS provides a unified framework for measuring and improving the reliability of AI-image detectors under conditions that better reflect real-world use.
Read the full abstract ▾
All authors Aleksandr Gushchin, Khaled Abud, Georgii Bychkov, Ekaterina Shumitskaya, Artem Filippov, Sergey Lavrushkin, Dmitriy S. Vatolin, Anastasia Antsiferova
Computational Geometry · Cross-listed from math.AT
A data structure for quotient flag complexes
Konstantin Sorokin, Aleksandr Levin, Maxim Beketov et al. (+1 more)
Vietoris-Rips filtrations, which are standard in topological data analysis, are flag complexes, and a simplex tree stores these without any attaching data. In this paper we ask what survives of this economy when a flag complex $K$ is divided by a subcomplex $A$, each connected component of $A$ being crushed to a point. Such a quotient is a CW complex whose
cells are the simplices of $K\setminus A$, but their attaching maps are no longer implicit. We show that for flag $K$ the face order of the quotient is strictly graded exactly when $A$ is flag, and that the surviving labelled
cells are determined by those of dimension at most 3. For $m$-flag pairs the threshold is $2m+1$, and it drops to $m+2$ when $K$ is flag. The prescribed
cells form a regular CW decomposition only when $A$ is full in $K$. These results justify the QF-tree: a
cell table that stores, for each surviving simplex, its ordered list of $d+1$ facets with collapsed facets flagged, indexed by a trie of quotient-vertex words. For bounded dimension its size is linear in the number of surviving simplices plus the retained provenance, and we derive and verify a simple formula for the collapsed fraction above which it is smaller than the homotopy-equivalent cone model. Because a collapse changes the attaching data only on the closed
star of $A$, the QF-tree can also be applied locally inside a simplex tree. For a ball-shaped $A$ in the sampled Vietoris–Rips regime the closed
star is a thin shell, and the median compact budget is below the cone model at every sampled radius. An accompanying library, modelled on Gudhi, implements the QF-tree, its local variant, an editable layer with local quotient updates, gluing, disc attachment, induced maps, cup products, fundamental-group presentations and zigzag persistence, and provided experiments separate the cost of maintaining a quotient from the cost of the
algebra computed on it.
Read the full abstract ▾
All authors Konstantin Sorokin, Aleksandr Levin, Maxim Beketov, Anton Ayzenberg
Social and Information Networks
Plan-to-Synthesis: Cross-City Human Mobility Generation via Semantic Latent Flow Matching
Zhoufu Wang, Baoshen Guo, Zhiqing Hong et al. (+6 more)
Human mobility generation aims to synthesize realistic point-of-interest (POI) visitation trajectories and has become an important tool for travel behavior modeling, transportation management, and urban planning. Existing
diffusion-based methods achieve high fidelity but require per-city generation, given the inherent heterogeneity of geospatial locations and POI categories, while large
language model-based methods generalize across cities but remain too costly at scale, especially for long-horizon trajectory generation. To address this, we propose SeMoFlow, a Semantic human Mobility generation framework based on latent Flow matching. We first encode heterogeneous POIs from different cities into a shared cross-city representation space via hierarchical Semantic IDs, where shared prefixes capture transferable semantics, and successive codes progressively refine the representation toward individual POIs. Building on the semantic IDs, SeMoFlow follows a plan-to-synthesis hierarchical generation paradigm, in which an autoregressive planner generates coarse-grained semantic and recurrence patterns, and a flow matching realizer synthesizes fine-grained suffix latents. The generated latents are subsequently decoded and grounded to concrete POIs. Extensive experiments on large-scale multi-city
datasets show that SeMoFlow achieves higher trajectory fidelity than existing baselines, preserves city-specific mobility motifs, and supports both joint multi-city generation and effective cross-city transfer. The code is available at \href{https://github.com/urban-mobility-generation/SeMoFlow}{https://github.com/urban-mobility-generation/SeMoFlow}.
Read the full abstract ▾
All authors Zhoufu Wang, Baoshen Guo, Zhiqing Hong, Junyi Li, Kailai Sun, Heye Huang, Alok Prakash, Shenhao Wang, Jinhua Zhao
Artificial Intelligence
SkillVine: Agent Skill Evolution via Branching Exploration
Kaiwei Liu, Jiqian Dong, Liran Dong et al. (+7 more)
Agent skills encapsulate reusable procedural knowledge that enables LLM
agents to perform tasks, and they can be improved automatically using trajectories from interactions with the environment. This is the classic problem of skill
evolution. Existing approaches predominately follow a linear
evolution paradigm, in which updates are sequentially applied to the latest skill-library version. As a result, they inevitably fall into local optima, leaving many promising
evolution paths unexplored. We propose SkillVine, an automatic skill-
evolution framework that formulates skill
evolution as a graph search problem and employs a branching exploration strategy. Equipped with a trunk-branch collaborative searching mechanism, an intelligent parent-node selector, and an adaptive-granularity update rule, SkillVine achieves a balance between exploration and exploitation. We evaluate SkillVine on 5
benchmarks with two LLMs. Results show that SkillVine discovers better skill-library versions along branches than along the linear trunk and achieves the best test performance in nine of ten
benchmark-model combinations.
Read the full abstract ▾
All authors Kaiwei Liu, Jiqian Dong, Liran Dong, Shuai Mao, Mingming Zhao, Bufang Yang, Jie Chuai, Zhitang Chen, Guoliang Xing, Zhenyu Yan
Information Theory · Cross-listed from stat.ML
Domain Adaptation with Target Information via Doubly-Anchored Distributionally Robust Optimization
David Kepplinger and Anand N. Vidyashankar
Domain Adaptation (DA) often lacks worst-case guarantees, while Distributionally Robust Optimization (DRO) based only on source data centers its ambiguity set at the source law and ignores available target structure. To bridge this gap, we introduce a doubly-anchored DRO framework whose ambiguity set is the intersection of $\phi$-divergence balls centered at the source law and a source-completed target reference law, the latter pairing the target
covariate law with the source conditional law. We derive dual-induced
adversarial bridge geometries for symmetric and asymmetric divergence pairings, notably introducing a Kullback–Leibler/squared-Hellinger (KL/HD) bridge. This asymmetric formulation yields a Lambert-$W$ geometry in which source-side exponential risk tilting and target-side Hellinger stabilization enter through distinct terms, attenuating, but not bounding, the effect of large likelihood ratios. Furthermore, without imposing
covariate shift, we establish finite-sample generalization bounds for the minimizer of a structural, loss-agnostic density-bridge risk under bounded-overlap conditions; these bounds do not apply directly to the loss-aware DRO min–max
estimator. We translate our framework into a bridge-weighted Nadaraya–Watson
estimator, proving uniform consistency for the source regression function and pointwise asymptotic normality, with target recovery when the source and target regression functions coincide, as under
covariate shift. Finally, an empirical evaluation on a domain-shifted Fashion-MNIST
dataset illustrates the finite-sample stability of the asymmetric KL/HD bridge under severe synthetic target-
covariate corruption.
Read the full abstract ▾