Discrete Mathematics · Cross-listed from math.CO
Proof of the Kahn Saks Conjecture
Max Aires
Let $\mathbb{P}(x\prec y)$ be the probability that $x$ precedes $y$ in a uniformly random linear extension of an $n$-element poset $P$, and define the balancing coefficient to be $\delta(x,y)=\min(\mathbb{P}(x\prec y),\mathbb{P}(y\prec x))$ with $\delta(P)=\max_{x,y}\delta(x,y)$. We prove (
Theorem 1) that sufficiently large width forces $\delta(P)$ to be arbitrarily close to $1/2$, answering a long-standing
conjecture of Kahn and Saks. In fact, we prove the stronger result (
Theorem 2) that large width forces one of two configurations in our poset: either a nearly uniform order on $k$ vertices, or an almost fixed order on $t$ vertices with one further vertex inserted uniformly among the $t+1$ slots. We also show that, for fixed $k$, the first possibility must occur within any antichain $X$ of size $\Omega(n^{2/3})$.
Read the full abstract ▾
Artificial Intelligence
Training Graph Foundation Models on The Web Graph
Ryoma Sato
We introduce Acacia, a graph foundation model, trained on the web graph. Acacia (i) supports arbitrary feature dimensionalities and semantics without additional training, (ii) supports a wide range of tasks, including node classification, link prediction, node clustering, and graph generation, without additional training, (iii) has in-context learning capabilities, and (iv) does not rely on pretrained LLMs. In particular, existing graph foundation models often require training additional classification heads or feature projectors to accommodate new graphs or new labels, whereas Acacia does not. Moreover, existing graph foundation models often gain their capabilities by being stitched together with pretrained LLMs, whereas Acacia is trained from scratch using only the Common Crawl web graph. This is also an important result because it provides evidence that graph models can acquire emergent capabilities from scratch like LLMs.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from eess.SP
Adaptive Pilot Selection for Unified Semantic Communication and Semantic Sensing in ISAC
Muhammad Abubakar Rashid, Muhammad Hannan Akram, Haejoon Jung et al. (+1 more)
Semantic communication (SemCom) and integrated sensing and communication (
ISAC) are promising technologies for future 6G wireless networks. Existing studies have applied semantic technology to either the communication module or the sensing module of
ISAC. In this work, we propose SemISAC, which performs both SemCom and semantic sensing within a single dual-function waveform. SemISAC uses a joint semantic encoder that extracts task-specific information for both communication and sensing. We evaluate SemISAC in a vehicular scenario in which vehicles share pixel-wise
segmentation of the road environment and, through sensing, classify surrounding objects and estimate their ranges. On the transmitter side, a deep learning encoder converts the input road-scene image into semantic symbols and places them on the data
cells of an OFDM grid, while the remaining
cells serve as pilots for channel state information estimation and sensing. The pilot configuration is adaptively optimized based on the channel conditions to balance communication and sensing requirements. At the receiver, a deep learning model reconstructs the
segmentation from the received waveform, while the transmitting vehicle captures the reflected waveforms from surrounding objects and uses task-specific deep learning decoders for target recognition and range estimation. Simulation results show that SemISAC achieves a
segmentation accuracy close to that of the dedicated SemCom module while outperforming both conventional and semantic baselines in target recognition and range estimation.
Read the full abstract ▾
All authors Muhammad Abubakar Rashid, Muhammad Hannan Akram, Haejoon Jung, Syed Ali Hassan
Human-Computer Interaction
From Segments to Trajectories: Evolving Affective Graphs with Evidence Retrieval for Continuous EEG Emotion Recognition
Chi Yang, Jihong Wang, Chengxi Xie et al. (+5 more)
Electroencephalography (
EEG)-based
emotion recognition is important for affective computing and human-computer interaction, yet most existing methods divide a long trial into short segments and assign each segment the label of its source trial. Although this strategy increases the number of training samples, it reduces an evolving emotional response to a segment-level, coarse-grained, and static prediction problem. In reality,
emotion may continuously emerge, intensify, weaken, and fluctuate as a stimulus unfolds, motivating the prediction of a time-aligned affective trajectory from the complete
EEG trial. This task requires coordinated modeling of how spatial neural organization evolves throughout the trial and how local emotional fluctuations interact with longer-term trends. In this work, we formally define and systematically investigate continuous
EEG emotion recognition as whole-trial affective trajectory prediction. We propose EAGER, an Evolving Affective Graph framework with Evidence
Retrieval for continuous
EEG emotion recognition. EAGER comprises two complementary modules: Affective State-guided
Topology Evolution models the evolving spatial organization of
EEG activity, while Multi-scale Temporal Evidence
Retrieval integrates short-term fluctuations with longer-range temporal trends for time-aligned prediction. Experiments on MAHNOB-HCI, SEED-VII, and REFED show consistent gains in trajectory-tracking metrics over representative methods, with competitive pointwise errors.
Read the full abstract ▾
All authors Chi Yang, Jihong Wang, Chengxi Xie, Kai He, Huan Liu, Man Yao, Shile Qi, Yuzhe Zhang
Robotics
PHASE: Compliance-Enabled Tactile Phase Retrieval for Few-Shot Insertion Learning
Jeremy Siburian, Cristian C. Beltran-Hernandez, Tatsuya Matsushima et al. (+3 more)
Contact-rich assembly tasks such as peg-in-hole insertion remain difficult to learn from limited demonstrations. While
retrieval-augmented imitation learning, which augments target demonstrations with relevant prior data, offers a promising direction, its applicability to contact-rich manipulation remains largely unexplored. Contact-rich insertion unfolds over multiple phases from search to insert, and retrieving phase-specific experience from prior data in principled ways remains an open question. Our key insight is that a compliant wrist enables the
robot to sustain contact throughout execution, producing rich tactile and force signals that naturally reveal the phase structure of insertion and inform what should be retrieved. Based on this insight, we present PHASE (PHase-Aware
Segmentation and
REtrieval), a framework for compliance-enabled tactile phase
retrieval that integrates
multimodal contact-aware representation learning, variable-length phase
segmentation from tactile signals, and phase-consistent
retrieval for policy learning. We evaluate PHASE on real-world peg-in-hole insertion across five peg geometries, comparing against
retrieval strategies drawn from state-of-the-art methods under a shared policy architecture. PHASE improves the overall success rate by 13 percentage points over the strongest non-phase-aware baseline, and improves performance under unseen initial positions by 30 percentage points. These results demonstrate that aligning
retrieval with interaction-defined contact phases substantially improves robustness in few-shot insertion learning.
Read the full abstract ▾
All authors Jeremy Siburian, Cristian C. Beltran-Hernandez, Tatsuya Matsushima, Yusuke Iwasawa, Masashi Hamaya, Mai Nishimura
Discrete Mathematics · Cross-listed from math.CO
Breaking the Infinite Barrier in the $\frac{1}{3}$–$\frac{2}{3}$ Conjecture
Max Aires, Swee Hong Chan, Igor Pak et al. (+1 more)
The balance constant is a poset parameter measuring how well random linear extensions can be split according to their relative order on two elements. We give an $\varepsilon$-improvement for the balance constant over the bound by Brightwell, Felsner and Trotter (1995), for some small $\varepsilon>0$. This is the first general result towards the $\frac{1}{3}$–$\frac{2}{3}$
conjecture in over 30 years.
Read the full abstract ▾
All authors Max Aires, Swee Hong Chan, Igor Pak, Greta Panova
Artificial Intelligence
From Tapping to Hopping: Augmenting Mobile GUI Agents with App-Native Deeplinks
Yuchen Sun, Chenglin Cai, Gongjie Zhang et al. (+8 more)
Mobile GUI
agents complete tasks using GUI actions like taps and swipes. These actions are broadly applicable across applications, but reaching a
navigation interface. A single deeplink call can replace a sequence of screen-by-screen GUI actions. We therefore introduce hybrid interaction, using deeplinks for direct
navigation and GUI actions for other on-screen operations and fallback. To enable this, we discover candidate deeplinks through static analysis, validate them on real devices, and describe their observed landing screens. This process creates a verified and grounded deeplink catalog that pairs each working deeplink with a description of its landing screen. Using this catalog, we introduce GUI-Hopper, a improves task success in commercial applications on real devices, further demonstrating the benefits of hybrid interaction.
Read the full abstract ▾
All authors Yuchen Sun, Chenglin Cai, Gongjie Zhang, Tianyu Xia, Quyu Kong, Panrong Tong, Zhengwen Zeng, Long Chen, Steven Hoi, Chongyang Zhang, Yue Wang
Machine Learning · Cross-listed from stat.ML
Conformal Prediction under Exponential-Tilt Joint Shift
Seungjin Choi
Conformal prediction can lose coverage when the data distribution changes after deployment. We study adaptation using labeled source data and unlabeled target inputs, allowing both the input distribution and its relationship with outcomes to change. We use Exponential Tilt Reweighting
Alignment (ExTRA), introduced for classification by Maity et al. (2023), to estimate structured distribution shifts. We compare using its estimated weights in conformal calibration with additionally tilting the source predictive distribution. Shared learned predictors, estimated weights, calibration samples, and test observations isolate the effect of tilting. Existing theory gives both procedures target coverage with true weights and a common coverage bound with estimated weights. Identification calculations and an analysis of how scoring interacts with weight estimation error help explain why their performance can nevertheless differ. In a synthetic regression setting where the assumed models match the data-generating process and target inputs are informative about the shift, tilting reduces mean set length by about $30\%$ relative to weighting alone, with both methods attaining coverage near nominal. Tilting can instead cause substantial coverage losses in synthetic classification and in regression when target inputs provide little information about the response shift. Real-data experiments also show no consistent benefit. Good coverage from weighted calibration alone does not ensure that adding predictive tilting will preserve coverage. Deciding when to apply this additional adjustment using only source labels and target inputs remains an open problem.
Read the full abstract ▾
Machine Learning · Cross-listed from math.OC
Retraction-Based Gradient Projection Algorithms on Manifolds
Conglong Xu and Hao Wu
We introduce a framework for retraction-based convex optimization on Riemannian
manifolds, which includes a notion of retraction-specific convex sets and retraction-based gradient projection
algorithms. The standard theory of gradient projection
algorithms generalizes easily to this framework. Within this framework, we establish convergence results for retraction-based gradient projection
algorithms with various stepsize rules. As an application, we use our framework to study the weighted low-rank approximation. We also provide numerical validation of our convergence results on the image completion task.
Read the full abstract ▾
Machine Learning
CacheReforge: Bounded Recovery for Stale KV Caches under Evolving Adapters
Yuhang Cao, Yanzhou Mu, Chunrong Fang et al. (+1 more)
Large
language models rely on KV caching to reduce repeated prefill computation in long context and interactive applications. As lightweight adapters evolve, cached states reflect earlier versions, so stale reuse distorts current model outputs, while complete affected suffix recomputation restores fidelity at substantial cost. We seek minimal recomputation that recovers current adapter behavior. Existing systems track
token, context, or stable adapter identity, but neither represent caches from earlier adapter versions nor distinguish update propagation from the recomputation required for behavioral recovery. To address these gaps, we introduce CacheReforge, which represents stale KV caches as layerwise mixed-version objects. It combines per-layer adapter anchors, calibrated sensitivity, accumulated drift, and executable restart boundaries to select direct reuse, bounded recomputation, or complete affected-suffix recovery. We distinguish dependency depth from the functional recomputation horizon and use cumulative tail influence to characterize when bounded recovery preserves current-model behavior. We evaluate CacheReforge on Qwen2.5-1.5B and Qwen2.5-7B with continual LoRA updates, including 16K HotpotQA and 2WikiMQA workloads. CacheReforge reduces mean KL divergence by 92.4% relative to stale reuse, while recomputing only 5.44% of layers and reducing cache-maintenance time by 93.2% relative to fresh full prefill. These results show that version-aware recovery preserves model fidelity and most KV caching gains.
Read the full abstract ▾
All authors Yuhang Cao, Yanzhou Mu, Chunrong Fang, Zhenyu Chen
Artificial Intelligence · Cross-listed from physics.soc-ph
Warned alike, AI agents avoid the less-crowded road while people take it
Takahiro Ezaki, Naoto Imura and Katsuhiro Nishinari
AI
agents built on a few shared models increasingly act for many people. A shared forecast about others can align their choices and change how scarce capacity is allocated. We tested this feedback in a two-road congestion game. Adding one sentence warning that others might follow a routing tip made populations of 50 GPT
agents crowd one road while avoiding the nearly empty alternative. Average travel time rose from 64 to 95 min, although any crowded-road
agent could have saved 69 min by switching alone. The warning discouraged the very move it predicted. The pattern persisted for 100 rounds. Two other model families shifted the same way without locking onto one road. Twelve all-human groups (240 participants) stayed near balance under numerical reports or the tip and warning. In 24 mixed groups with a further 240 participants, imbalance grew with the share of
agents in the registered analysis, while people increasingly took the road the
agents avoided. Collective costs stayed below the allagent reference, but with 15
agents and 5 humans,
agent seats averaged 80 min, compared with 44 min for human seats. Shared forecasts can thus sustain collective inefficiency among similar
agents. A better group average can also hide an unequal burden. Evaluations of AI
agents that share resources should test populations, treat messages as interventions and report who bears the costs.
Read the full abstract ▾
Computation and Language
Effects of Transcript Compression on LLM-based Medical Misinformation Detection in Japanese YouTube Videos
Yuya Wake, Sho Tsugawa and Toshiyuki Amagasa
Large
language models (LLMs) are increasingly used to assess long-form medical
videos, but their effectiveness may depend on whether transcripts are provided in full or compressed through summarization,
retrieval, or claim screening. This study examines how such transcript compression affects LLM-based veracity classification of Japanese medical YouTube
videos. We compare four transcript input designs: full transcripts, LLM-generated summaries, RAPTOR-based retrievalaugmented generation (RAG), and Screening, which extracts candidate medical and health-related sentences. Using 74 long-form
videos labeled as Real or Fake, we evaluate classification performance and analyze linguistic changes using J-LIWC, hedge expressions, and institutional or technical terms. The full-transcript Baseline achieved the best performance, whereas all compressed inputs increased false negatives, meaning that Fake
videos were more likely to be misclassified as Real. Summary caused the largest performance drop, while Screening performed best among the compressed inputs but still omitted many medically relevant sentences. Linguistic analyses showed that these errors were not explained by a simple increase in certainty. Instead, Summary reduced affective, social, temporal, cognitive, and conversational cues, while Summary and RAG made institutional and technical terms more salient. These findings suggest that transcript compression can represent Fake
videos as more coherent and authoritative inputs, thereby weakening cues needed for misinformation detection
Read the full abstract ▾
Artificial Intelligence
EXAONE Demand 1.0: A Time Series Foundation Model for Demand Forecasting
Seunghan Lee, Sangjun Han, Jun Seo et al. (+9 more)
Time series foundation models (TSFMs) are pretrained on series from diverse domains, where demand series make up only a small fraction. Demand data has properties that such corpora rarely contain: Short histories, frequent zeros, censoring by stock-outs, and exogenous events that the series does not record. To this end, we propose EXAONE Demand, built on 1) a demand-specific corpus and 2) a demand-aware adapter. For the corpus, we assemble 11.3M series and 48.4B observations from 73 sources, and a synthetic generator supplies the behaviour that open demand data under-represents. For the adapter, we attach low-rank branches to a frozen general-domain backbone, one for each of the four demand classes (smooth, intermittent, erratic, and lumpy), and a router that reads eight scale-free statistics of the input series decides how much each branch contributes. We build EXAONE Demand in two versions, one trained on real-world and synthetic demand together and one trained on the synthetic corpus alone. On 22 held-out
datasets, both versions outperform 36 TSFMs, and real-world demand adds a gain over synthetic data alone.
Read the full abstract ▾
All authors Seunghan Lee, Sangjun Han, Jun Seo, Junhyeok Kang, Jaehoon Lee, Tae Yoon Lim, Dongwan Kang, Hwanil Choi, Minjae Kim, Sungdong Yoo, Soonyoung Lee, Wonbin Ahn
Artificial Intelligence
TISD: On-Policy Self-Distillation with Trajectory Intervention
Taeckyung Lee, Rinat Amankos, Jeonghye Kim et al. (+3 more)
On-policy self-
distillation (OPSD) provides dense teacher targets, but evaluates them only along student-sampled rollouts. When the privileged teacher favors an alternative action at a visited prefix, OPSD can provide a target for the branch decision but cannot supervise the successor contexts induced by that action unless the student samples it. This creates a training-time data-collection bottleneck and suggests a different role for teacher-student disagreement: proposing a trajectory branch rather than identifying a sufficient local repair. Our diagnostic framework using controlled
token interventions reveals that a teacher-preferred
token at peak disagreement can improve student continuation success, while its local corrective value is limited. Motivated by this finding, we introduce a simple branch-regenerate-distill
algorithm, Trajectory-Intervention Self-
Distillation (TISD). TISD forces a teacher-selected branch action, returns suffix generation to the student, and distills the full trajectory under the privileged-context-conditioned teacher. Across the coding models, TISD improves average Avg@4 over SDPO by 1.2 percentage points. Across the science domains, it improves average Avg@128 by 0.8 points under an equal-step budget and by 0.3 points under an equal-time budget. These results support teacher-guided branching as a way to expose useful successor contexts for self-
distillation.
Read the full abstract ▾
All authors Taeckyung Lee, Rinat Amankos, Jeonghye Kim, Hyungjun Yoon, Woogyeol Jin, Sung-Ju Lee
Machine Learning · Cross-listed from math.OC
Tight Stochastic Condition-Number Dependence in Nonconvex-Strongly-Concave Minimax Optimization
Qihao Zhou
We study whether the linear condition-number dependence in the
stochastic complexity of SAPD+ is necessary for nonconvex-strongly-concave minimax optimization. For jointly $L$-smooth objectives with dual strong-concavity parameter $\mu$, we prove a lower bound that matches the SAPD+ upper bound under the same Moreau-envelope stationarity criterion and the same primal-dual initialization gap. Specifically, when $\sigma\ge\varepsilon$, the worst-case complexity of zero-respecting
algorithms is $\Theta(\kappa LG\sigma^2\varepsilon^{-4})$ in the stated accuracy regime, where $\kappa=L/\mu$, $G$ bounds the initial primal-dual gap, and $\sigma^2$ bounds the variance of a general unbiased first-order oracle. The lower bound is realized on a smooth problem class with a bounded dual box. Our construction routes each link of a nonconvex zero-chain through a dual gradient of magnitude proportional to $\varepsilon/\sqrt{\kappa}$, while an undiscovered primal coordinate prevents stationarity. It also yields the primal-gradient lower bound $\Omega(L\Delta(\sqrt{\kappa}\varepsilon^{-2}+\kappa\sigma^2\varepsilon^{-4}))$ after combination with the known deterministic bound, where $\Delta$ bounds the initial primal function gap.
Read the full abstract ▾
Numerical Analysis
A vanishing-viscosity minimizing movement Fourier spectral method for scalar conservation laws
Lun Ji, Buyang Li and Fangyan Yao
We propose a vanishing-viscosity minimizing movement (VVMM)
Fourier spectral method for scalar
hyperbolic conservation laws under periodic boundary conditions. The method is a fully discrete space–time residual-minimizing scheme,
Fourier spectral in space and
polynomial in time, stabilized by vanishing viscosity and heat-kernel postprocessing. A basic analytical difficulty in
Fourier discretizations of nonlinear conservation laws is the interaction between
Fourier projection and the nonlinear flux; the resulting projection residual contains unresolved high-frequency components. VVMM addresses this issue by selecting, on each time slab, the numerical solution that minimizes {a penalized cut-off viscous conservation laws residual} and then applies heat-kernel postprocessing to damp unresolved modes. We prove a fully discrete $L^1$ error estimate, in any fixed space dimension, that separates the vanishing-viscosity error, the temporal interpolation error, and the spatial
Fourier truncation error. {Under exact minimization of the penalized cut-off residual and suitable parameter coupling,} the estimate yields, for each fixed $\gamma>0$, an $L^1$ convergence rate $N^{-1/2+\gamma}$, with a constant depending on $\gamma$. Numerical experiments in one and two dimensions illustrate stable shock capturing without visible Gibbs oscillations and convergence behavior consistent with the theory.
Read the full abstract ▾
Robotics
A Second Torque Port for Series Elastic Actuators: Parallel-Integrated Design and Time-Scale Torque Allocation
Donghao Jia, Xiubo Xia, Junhang Liu et al. (+3 more)
A series elastic actuator has a single torque port and pays for it twice: the geared motor must swing its own reflected inertia through the spring, so the amplitude it delivers collapses as $\omega^{-2}$ in the command frequency $\omega$ once it saturates, while commands below the transmission's breakaway friction never arrive at all. This letter opens a second torque port on the load side, placing a frameless direct-drive micro motor in parallel with a fixed-stiffness spring – a parallel-integrated SEA, or Pi-SEA, whose delivered torque is read from spring deflection and micro current without a sensor – and dividing the commanded torque between the two channels by time scale rather than by filter design. The micro torque loop is the fast subsystem, which makes the closed loop singularly perturbed and turns the separation the channels need into a bound to check rather than a crossover to tune; a leaky mid-ranging integrator returns the steady load to the spring; and the amplitude ceiling, read backwards, becomes a closed-form sizing rule that matches spring, geared motor and micro motor to the amplitudes and frequencies an application asks for. Against SEAs, the Pi-SEA widens the tracked band at small amplitudes and lowers the residual the joint imposes on its environment, each by an order of magnitude.
Read the full abstract ▾
All authors Donghao Jia, Xiubo Xia, Junhang Liu, Zeyu Zhu, Xiaoyu Geng, Jian Sun
Robotics
VLaRL: Augmenting Vision-Language-Action Models with Simulation-Trained Latent-Conditioned Residual RL
Namiko Saito, Kinam Kim, Heecheol Kim et al. (+2 more)
Vision-
language-action (VLA) models provide broad, instruction-conditioned manipulation behaviors, but their physical execution can remain imprecise during contact-rich interaction. Residual reinforcement learning (RL) can correct such errors while keeping the VLA frozen, but real-
robot RL is costly and safety-critical. We propose VLA Latent-Conditioned RL (VLaRL), which enables residual RL for frozen VLAs to be trained in simulation and deployed on real
robots without real-world RL or online adaptation. The key challenge is transferring the learned residual policy despite the visual gap between simulation and reality. Rather than requiring pixel-level visual correspondence, VLaRL uses the VLA's internal
vision-
language latent representation to condition residual control and as the sim-to-real transfer interface, and learns a lightweight mapper that transforms simulation-derived latents toward the real latent distribution. Across four contact-rich manipulation tasks and two VLA backbones, VLaRL improves real-world success in all task-backbone combinations, while controlled ablations demonstrate the importance of both latent conditioning and latent
alignment for transferring simulation-trained residual control.
Read the full abstract ▾
All authors Namiko Saito, Kinam Kim, Heecheol Kim, Katsushi Ikeuchi, Yasuyuki Matsushita
Computation and Language
Evidence-Grounded Auditing of Identification Assumptions in Climate-Policy Causal Evaluations
Yonghong Zhang, Yong Xie, Isabel M. Parra et al. (+1 more)
Difference-in-differences (DID) studies are widely used to evaluate
climate policy, but assessing the evidence supporting their identification assumptions remains challenging. We introduce ARGUS, a structured
language-model pipeline that audits reported evidence against an eleven-dimension assumption-implication-evidence rubric and abstains when relevant evidence cannot be retrieved. We evaluate ARGUS using injected flaws, economics papers, and a small pilot with reconciled labels. On the 11-flaw
benchmark, ARGUS detects 73% of planted flaws, compared with 18% for a keyword-based pipeline. Across 26 economics papers, ARGUS abstains on about 40% of paper-dimension assessments for lack of retrievable evidence. In a five-paper pilot with labels reconciled by two annotators, it assigns a higher risk level than the labels on 25 of the 33 assessments it completes. A rule fixed before the labels arrived removes most of this in-sample; weighted agreement stays low. ARGUS provides evidence-linked risk reports that localize potential weaknesses for expert review, without adjudicating causal claims. Code and data: https://github.com/yonghongzhang-io/ARGUS
Read the full abstract ▾
All authors Yonghong Zhang, Yong Xie, Isabel M. Parra, Ricardo Correia
Computer Vision · Cross-listed from cond-mat.mtrl-sci
Universal Drift Correction for Multidimensional Scanning Microscopy
Sangjoon Lee, William Millsaps, Dasol Yoon et al. (+7 more)
In scanning microscopy, drift causes the specimen to be sampled at positions displaced from the nominal probe positions. This displacement alters the spatial assignment of the recorded signals and biases quantitative measurements across two-dimensional imaging, channel-resolved spectroscopic mapping, and scan-position-resolved diffraction analysis. Here, we extend orthogonal-scan drift correction from 2D images to spectrum images and diffraction
datasets. We demonstrate how to recover probe positions using either differently oriented multidimensional scans or structural reference images. The recovered positions are used either to resample the multidimensional data onto a regular grid or to assign each recorded signal to its corrected coordinate. Our method combines affine and non-rigid correction, requires no prior structural model, and is implemented as open-source, GPU-accelerated software that reduces processing times by two to three orders of magnitude, enabling routine and automated drift correction for quantitative multidimensional microscopy.
Read the full abstract ▾
All authors Sangjoon Lee, William Millsaps, Dasol Yoon, Caitlyn Obrero, Guoliang Hu, Corrie Barnes, Cedric Lim, Andrew Barnum, Arthur R. C. McCray, Colin Ophus
Computer Vision
Reliability-Regulated Trajectory Optimization for Progressive COLMAP-Free 3D Gaussian Splatting
Zijian Wu, Jinliang Wang, Zidian Lin et al. (+5 more)
COLMAP-free 3D Gaussian Splatting (3DGS) bypasses computationally expensive structure-from-motion (SfM) pipelines, yet progressive camera pose tracking remains fundamentally vulnerable to error compounding—early pairwise tracking inaccuracies both corrupt subsequent frame initializations and remain permanently frozen in the scene representation. Rather than relying on heavyweight external neural priors or treating progressive tracking through isolated heuristic fixes, we propose a unified reliability-regulated trajectory optimization framework for progressive COLMAP-free 3DGS. At its core, our framework establishes an intrinsic, self-supervised bidirectional cycle-consistency mechanism that systematically regulates progressive camera trajectory estimation across two complementary temporal horizons: (1) Forward Motion Propagation, where the online reliability signal adaptively gates first-order kinematic warm-starts of rigid motion into upcoming pairwise registrations, supplying informed directional search priors while safely intercepting untrusted transitions; and (2) Retrospective Trajectory Correction, where the same reliability signal dynamically weights relative-pose consistency constraints within a sliding window of neighboring camera poses. By governing both prospective state initialization and retrospective trajectory consolidation through a unified reliability regulator, our self-contained framework resolves progressive drift without external priors or offline preprocessing. Extensive evaluations on Tanks and Temples and CO3D-V2
benchmarks show that our method substantially improves camera trajectory accuracy and novel-view rendering quality, outperforming existing unposed baselines. Code is available at https://github.com/Zijian1026/RRTO-CF3DGS.
Read the full abstract ▾
All authors Zijian Wu, Jinliang Wang, Zidian Lin, Ying Song, Ziqian Lu, Hanjie Ma, Zhen Ye, Mingfeng Jiang
Computation and Language
Haixu Ma, Saad Lahrichi, Weiwei Li et al. (+11 more)
Black-box On-Policy
Distillation (OPD) seeks to improve a student from its own generations when the teacher provides sampled responses but not
token probabilities.
Adversarial distillation offers one route: it learns a discriminator over
prompt-matched teacher and student responses and uses its score as the policy reward. However, sampling discriminator negatives from the latest student at each step couples the learned reward to a negative distribution that changes after every policy update. We address this moving-target problem with persistent-negative
adversarial distillation, a live-pool method that replaces a fraction of each discriminator batch with historical,
prompt-matched teacher–student comparisons. Under matched discriminator compute, historical comparisons train the discriminator, while GRPO remains on-policy with fresh student responses. Our analysis identifies the Bayes-optimal reward as a teacher-to-negative log-density ratio and, under explicit assumptions, shows how persistent negatives anchor the discriminator and reduce reward-estimation MSE relative to fresh-negative training. Across two student families, three judges, and four judged-chat
benchmarks, persistent-negative
adversarial distillation consistently improves performance over current methods at matched discriminator compute. It also yields smoother fresh-policy discriminator trajectories, with fewer below-chance dips. These findings identify the discriminator's negative distribution as an important design axis in black-box on-policy
distillation.
Read the full abstract ▾
All authors Haixu Ma, Saad Lahrichi, Weiwei Li, Kevin Han, Weiqiang Wu, Peggy Yang, Dongzhuo Li, Ruiyi Li, Serena Li, Gedi Zhou, Mingze Gao, Abhishek Kumar, Xiangjun Fan, Lizhu Zhang
Software Engineering
Developing a Roadmap to an AI-first Organization: A Case Study in Embedded Software Development
Viktor Kjellberg, Srijita Basu, Simin Sun et al. (+2 more)
The emergence of AI
agents is expected to reshape software engineering by moving beyond AI as assistants towards systems capable of planning, executing, and evaluating development tasks with increasing autonomy. This transition is particularly significant for embedded software organizations, where strict requirements for quality, traceability, verification, and long-term maintainability often apply. This paper presents a case study of a large embedded systems company and its transition toward becoming an AI-first organization. Through a mixed method, we analyzed data collected from a semi-structured workshop with 40 participants, including scrum masters, architects, management, and product owners. The findings show that the participants expect agentic AI to affect team structure, required competencies, organizational strategies, and developers' roles within the organization. Based on these findings, the paper discusses implications for
federated AI team formation, human-in-the-loop practices in such an organization, and the sustainable adoption of AI
agents in embedded software engineering. We also present a concrete roadmap for the organization towards becoming an AI-first organization.
Read the full abstract ▾
All authors Viktor Kjellberg, Srijita Basu, Simin Sun, Farnaz Fotrousi, Miroslaw Staron
Performance
Evaluation of portability and performance of an OpenMP5 offloaded Quantum-Inspired Evolutionary Optimization Across the GPU Ecosystem
Kasturi Venkata Srikanth, Ashish Singh, Ferdin Sagai Don Bosco et al. (+4 more)
Quantum-inspired evolutionary optimization (QIEO) is a new class of population-based metaheuristic optimization
algorithms which represents design variables as a set of
qubits and searches a continuous, multi-dimensional landscape through rotation of the
qubit's amplitude pair. Every generation rotates those amplitudes toward a single elite, which corresponds to that generation's best. The per-generation cost scales as $O(N_p N_g)$ for $N_p$ chromosomes and $N_g$ genes (decision variables). Production use of such solvers is rarely confined to a single machine class. Prototypes are run on laboratory servers- before moving to rented cloud workstations for more involved campaigns. The largest problems are reserved for leadership-class accelerators. This paper asks whether a single OpenMP~5 source of QIEO, offloaded with \#pragma omp target, is a viable production path in each of those settings. We report three independent, campaigns of the 0/1 knapsack problem against a same-source multi-core Intel CPU baseline. The study comprises approximately 3,000 runs spanning varying chromosome and gene counts, evaluated using both chromosome-level and gene-level offload strategies on the NVIDIA Tesla V100 SXM2, NVIDIA A100 80GB, and AMD Instinct MI300X GPUs. Deployment-specific nuances such as Volta's constant-
memory cliffs, Ampere's L2 persistence and cp.async, CDNA~3's Infinity Cache and XCD occupancy are addressed to ensure high performance of these platforms. Results reveal gene-parallel offload achieved
geometric-mean speedups of 90$\times$, 136$\times$, and 155$\times$ over a single CPU core on the V100, A100, and MI300X, respectively, and 12$\times$, 17$\times$, and 16.6$\times$ over 72 host threads. Furthermore DetermineElite, the $O(N_p)$ selection of the generation-best chromosome, is found to be better suited to the host than to the device.
Read the full abstract ▾
All authors Kasturi Venkata Srikanth, Ashish Singh, Ferdin Sagai Don Bosco, Aman Mittal, Abhishek Singh, Aditya Singh, Abhishek Chopra
Artificial Intelligence
SkillEvoReg: Regularizing Agent Skill Evolution Against Overfitting
Guanyu Nie, Fangzhou Zhu, Shixiong Kai et al. (+3 more)
Language-model
agents increasingly improve by converting execution experience into reusable external skills. Yet repeated skill updates form a learning process of their own: locally useful edits can accumulate into redundant or task-specific instructions, while new updates can disrupt behavior that previously worked. We study this problem as skill-
evolution overfitting and introduce SkillEvoReg, a general regularization framework for skill
evolution inspired by anti-overfitting techniques in neural-network training. SkillEvoReg combines training-time skill dropout, which perturbs update generation, and complexity-aware local regularization, which controls unnecessary structural growth, with causal counterexample validation (CCV), which provides targeted behavioral validation of candidate-specific regressions. We instantiate the framework across heterogeneous skill-
evolution systems while retaining each system's native skill evolver and task evaluator. Across SkillOpt, SkillEvolBench, and ContinualSkillBench, SkillEvoReg consistently controls skill-state growth while preserving competitive downstream capability, improves several transfer and later-stage
evolution outcomes, and identifies update-level regressions that structural metrics alone cannot reveal. These results suggest that explicit regularization is a useful complement to increasingly capable skill updaters.
Read the full abstract ▾
All authors Guanyu Nie, Fangzhou Zhu, Shixiong Kai, Xiongwei Han, Tao Zhong, Mingxuan Yuan
Systems and Control
AC Power Flow Contingency Analysis Using a Single Deep Neural Network
Md Obaidur Rahman, Junjie Qin and Vassilis Kekatos
Contingency analysis using the AC power flow (AC-PF) model is a critical tool for accurate grid security assessment, but its computational burden increases with the number of operating scenarios and outage configurations to evaluate. Recent ML-based approaches typically require outage-specific training data, leading to offline training costs that scale with the number of contingencies. This work proposes a framework that reuses a single ML model trained solely on basecase AC-PF data to estimate post-contingency operating states under arbitrary single-line outages. The proposed approach formulates post-contingency state prediction as a fixed-point iteration. If the ML model is a deep neural network (DNN), we derive sufficient conditions that guarantee convergence and develop semidefinite programming (SDP) formulations to certify these conditions for a given DNN. Numerical tests on the IEEE 118-bus system demonstrate that the proposed SDP formulations are tight, that the certified conditions hold for all tested contingencies, and that the resulting method produces accurate post-contingency state estimates within only a few iterations.
Read the full abstract ▾
Machine Learning
Learning Chance-Constrained MDPs with Bellman Distributional Certificates
Chenbei Lu and Hongyu Yi
Safe reinforcement learning (RL) commonly enforces expected-cost constraints, but such expectation safety may fail to control the probability of rare high-cost trajectories. Chance-constrained MDPs (CCMDPs) impose a stronger probability-level requirement, but are widely viewed as harder because the chance constraint is nonconvex and depends on the full trajectory rather than a Bellman-linear expectation. In this paper, we reveal that this computational difficulty does not necessarily imply a higher statistical price. For tabular discounted CCMDPs with fixed bounded successor support and access to a certified planning oracle, we establish a model-based upper bound, with a matching lower bound up to logarithmic terms. Technically, our key idea is the Bellman distributional certificate, which constructs a Bellman recursion for constraint violation probabilities before policy selection. The certificate can be reused across candidate policies; combined with shared row-wise reverse-KL confidence sets, it gives a policy-uniform trajectory-KL transfer without a union bound over policies or time–budget Bellman tables. For
stochastic policies, we give a model-free variance-reduced policy-gradient
algorithm with a finite-sample expected KKT-residual guarantee and independent validation of every accepted policy. Numerical experiments on synthetic CCMDPs and an IEEE 14-bus energy storage control
benchmark illustrate the safety and mechanism behavior of the proposed
algorithms.
Read the full abstract ▾
Computer Vision
MDSkin-Net: Multi-Task Skin Lesion Analysis Driven by Pattern Analysis Priors and Spatial Alignment Regularization
Yijian Li, Saad Bedros, Paul Bigliardi et al. (+3 more)
Reliable skin lesion
segmentation and classification are central to dermoscopic computer-aided diagnosis. Existing multi-task frameworks couple the two tasks architecturally without clinical knowledge, while knowledge-injecting approaches rely on the macroscopic ABCD rule, which was not designed for dermoscopy. Dermoscopic diagnosis is grounded in Pattern Analysis, a microscopic framework structured around dermoscopic features. We propose MDSkin-Net, which incorporates cue-level Pattern Analysis priors into a hybrid CNN-
Transformer architecture. At its core is a Pattern Analysis-Guided
Attention Module (PAGAM) comprising three priors motivated by distinct dermoscopic cues: an improved Efficient Channel
Attention (iECA), a Multi-Scale Spatial
Attention (MSSA), and a Biased Asymmetry
Attention (BAA). We further introduce a multi-scale spatial
alignment regularization (MSAR) that uses the
segmentation ground-truth mask as hierarchical soft supervision, confining the classification head to lesion-localized evidence and coupling both task pathways through a shared spatial prior. Trained exclusively on the ISIC 2017 training split without external dermoscopy data, the MDSkin-Net ensemble transfers robustly under zero-shot evaluation, reaching a Dice Similarity Coefficient (DSC) of 92.38% and a melanoma AUC of 97.84%on PH2, and a DSC of 88.92% on the ISIC 2018 Task 1 test set. On the in-domain ISIC 2017
benchmark, the ensemble attains a mean Area Under the Curve (AUC) of 91.60% across the two classification tasks (melanoma and seborrheic keratosis vs. rest), and a DSC of 84.72% for
segmentation. Classification remains competitive with baselines; in-domain
segmentation trails single-task specialists, yet the proposed priors and
alignment regularization yield representations that generalize consistently across cohorts of different scales.
Read the full abstract ▾
All authors Yijian Li, Saad Bedros, Paul Bigliardi, Mei Bigliardi Qi, Vassilios Morellas, Nikolaos Papanikolopoulos
Distributed Computing
The KV Cache Is the New Memory Wall
Tejinder Singh
Autoregressive LLM inference at long context is bounded by
memory bandwidth, not arithmetic throughput, and the binding resource shifts from model weights to the Key-Value (KV) cache as sequence length grows. For Llama-3-70B in BF16, the 140 GB weight footprint exceeds the 80 GB HBM of a single accelerator, and one 128k-
token sequence adds 42 GB of KV cache. Techniques that compress, evict, page, share, or offload KV state have proliferated, but reported gains use inconsistent workloads, hardware, and quality metrics, preventing cross-paper comparison. This SoK paper unifies the field analytically, with a protocol that strictly separates derived and reported claims. We derive closed-form arithmetic intensity as a decaying function of context length, parameterized by hardware
topology for NVIDIA H100, NVIDIA B200, and AMD MI300X, including per-die bandwidth partitioning and the crossover lengths where KV traffic overtakes weight traffic. We classify the literature into five domains, quantization,
token eviction, KV paging, prefix caching, and heterogeneous tiering, evaluating one method per domain at 128k context under a single protocol. The central finding is a three-regime structure: below a hardware-specific crossover, weight traffic dominates and KV compression yields negligible speedup; beyond it, KV traffic dominates and each domain trades quality for bandwidth savings approaching the roofline bound. Paging and prefix sharing are lossless but address capacity, not bandwidth. Quantization and eviction cut bandwidth directly, with degradation that accelerates below 4-bit precision and turns discontinuous for eviction on position-sensitive tasks. Tiering converts the bandwidth wall into an interconnect problem bounded by PCIe or NVLink rather than HBM. We close with design rules for selecting a compression domain given hardware, context length, and quality budget.
Read the full abstract ▾
Data Structures and Algorithms · Cross-listed from math.OC
Faster Linear Programming with $\sqrt{\mathrm{rank}}$ Linear System Solves
Zhao Song
Lee and Sidford [LS19] showed that the linear program $\min\{c^\top x\ :\ A^\top x=b,\ l\leq x\leq u\}$ over $x\in\mathbb{R}^m$, where $A\in\mathbb{R}^{m\times n}$, can be solved to accuracy $\epsilon$ using $O(\sqrt n\log^{13}m\cdot\log(mU/\epsilon))$ solves of linear systems in $A^\top\mathbf DA$ for positive diagonal
matrices $\mathbf D$, where $U$ bounds the magnitudes of the input and of the initial point. Theirs is the first such bound governed by $\mathrm{rank}(A)=n$ rather than by the number of constraints $m$. Song [Son19] mentioned that reducing the $\log^{13}m$ factor is an interesting future direction. Given an interior point and a finite certified magnitude bound $U$, we give an
algorithm that uses $O(\sqrt n\log^{4}m\cdot\log(mU/\epsilon))$ solves of such linear systems, improving the Lee–Sidford bound by a factor of $\log^{9}m$. We
conjecture that $O(\sqrt n\log(mU/\epsilon))$ such linear-system solves suffice.
Read the full abstract ▾