Machine Learning
Differentiable RNA Secondary Structure Extraction for Deep Learning
Tyler Illman, Max Ward, Marcell Szikszai et al. (+1 more)
Many deep learning approaches to RNA secondary structure prediction have recently been proposed. They typically output a weight
matrix $W$ where $W_{ij}$ is an arbitrary weight for base $i$ pairing with base $j$. Converting this
matrix to a predicted secondary structure or base-pairing probability
matrix typically involves ad hoc and problematic downstream
algorithms. Despite the importance of this conversion step, which we refer to as structure extraction, it has received relatively little
attention in the literature. In this work, we analyze how the congruence between training and extraction methods affects prediction performance. To do this, we compare four extraction
algorithms: a Nussinov-like dynamic programming method, maximum-weight graph matching and the greedy extraction
algorithms used by SPOT-RNA and RiNALMo. These are evaluated on outputs from the pretrained RiNALMo model and three toy models trained in this paper: a differentiable Nussinov-like model, a binary cross-
entropy (BCE) baseline, and a model that incorporates a novel symmetric doubly
stochastic matrix (SDSM) normalization
algorithm during training which allows it to output base-pairing probability
matrices directly, without a separate extraction step. This SDSM normalization
algorithm is differentiable and can be added inline to any deep learning model during training and evaluation. We find that the performance of each extraction method depends strongly on how the corresponding model was trained. Considering the toy models themselves, the SDSM model showed the strongest overall performance: it outperformed the BCE baseline under all four extraction
algorithms and produced pre-extraction outputs closest to the ground truth. These results suggest that SDSM normalization is a tractable alternative to traditional structure extraction.
Read the full abstract ▾
All authors Tyler Illman, Max Ward, Marcell Szikszai, Ryan K. Krueger
Artificial Intelligence
Backbone-Adaptive Evidence Routing for Robust Pairwise LLM Judging
Zeyan Li, Jing Peng and Jianfeng Xu
Pairwise
language-model judges can gather evidence through direct comparison,
reasoning, or reference-based verification, but no single protocol is best across
benchmarks and judge backbones. We introduce Backbone-Adaptive Evidence Routing (BAER), which adapts the evidence mechanism while preserving candidate
symmetry: swapping the two responses may reverse the preference but cannot change its strength. BAER separates each expert's signed preference from candidate-invariant reliability and builds three symmetric heads: evidence stacking, reliability-based expert routing, and candidate-blind reference verification. Development data select one head for each
benchmark–backbone condition, and that choice is frozen before testing. Across four
benchmarks and two 8B judge backbones, BAER achieves the highest test accuracy among the compared methods in all eight conditions, with full prediction coverage and gains of 0.87–7.32 points over the strongest external baseline. The results show that adapting how evidence is gathered is more reliable than fixing one judging protocol everywhere.
Read the full abstract ▾
Numerical Analysis
Sparsely connected rank-inspired neural network
Yunqing Huang, Wu Su, Nianyu Yi et al. (+1 more)
We propose a Sparsely Connected Rank-Inspired Neural Network (SCRINN) for function approximation and the numerical solution of partial differential equations (PDEs). By introducing a structured sparse connectivity architecture and an orthogonality- and normalization-guided loss function, SCRINN constructs an approximately orthonormal neural basis while promoting progressive rank growth of its evaluation
matrix and reducing the number of trainable parameters. A two-stage framework is developed, in which an approximately orthonormal neural basis is first constructed, and the output weights are subsequently determined using least-squares methods. Numerical experiments on function approximation and a variety of steady-state, time-dependent, and nonlinear PDEs demonstrate that SCRINN consistently achieves high approximation accuracy with substantially lower training costs. The code is publicly available on GitHub.
Read the full abstract ▾
All authors Yunqing Huang, Wu Su, Nianyu Yi, Peimeng Yin
Artificial Intelligence
ORCA: Evaluating LLMs on Data Science Code Translation
Xiaolong Li, Jinyang Li, Bowen Qin et al. (+5 more)
Data Science Code Translation (DSCT) is the process of converting code between data science libraries while preserving functional equivalence and enabling interoperability across data science ecosystems. While Large
Language Models (LLMs) have demonstrated considerable progress in Data Science Code Generation (DSCG), their performance in DSCT remains insufficiently studied. To address this gap, we introduce ORCA, a comprehensive
benchmark with two complementary settings: ORCA-MAIN, which comprises 1,600 carefully curated grounding-level tasks across 3 representative domains: Data Querying, Data Manipulation, and Deep Learning; and ORCA-PROJECT, which contains 200 translation tasks over complete data science projects across 7 data science task types. Each task is accompanied by annotated reference translations and test cases for validating functional equivalence. We further incorporate a multi-stage quality verification process that thoroughly verifies task correctness and test case robustness. Experimental results demonstrate challenges in DSCT, with even frontier LLMs showing limited performance. Specifically, Claude-Opus-4.6 achieves a success rate of 56.92% on ORCA-MAIN and 33.67% on ORCA-PROJECT, indicating considerable room for improvement in DSCT. We also observe a clear directional preference in DSCT, where translation is consistently easier when the source code expresses the task through more explicit, fine-grained operations. Motivated by this, we propose an intent-augmented method, in which the model first infers source-code intent and then uses it as additional context for translation, achieving average absolute success-rate gains of 4.80% and 5.33% on ORCA-MAIN and ORCA-PROJECT, respectively.
Read the full abstract ▾
All authors Xiaolong Li, Jinyang Li, Bowen Qin, Ge Qu, Nan Huo, Xiaohan Xu, Shipei Lin, Reynold Cheng
Computers and Society
Beyond the Last Truffula Tree: SustainAI - A Water-Aware, Closed-Loop Framework for Environmentally Accountable AI
Farnaz Farid, Tashfia Towkee, Sania Nasreen et al. (+1 more)
As artificial intelligence (AI) becomes embedded in everyday life, its environmental footprint, particularly water consumption remains largely invisible. While energy and carbon impacts are widely recognized, the substantial freshwater demands of data center cooling and electricity generation receive little
attention. To address this gap, we introduce SustainAI, a water-aware, closed-loop framework incorporating environmental accountability into AI deployment. SustainAI integrates real-time water metering, a
hallucination-aware penalty model, and a water-aware routing
algorithm that accounts for regional water stress. Evaluated via Small
Language Models (SLMs) extracting health misinformation, results reveal an 11-fold variation in water footprint across geographically distributed data centers (0.0477 mL to 0.5360 mL per inference). Across 1,335 inference runs, the system consumed approximately 399 mL of water but produced only 240 correct outputs, demonstrating that substantial resources are spent on inaccurate responses. Crucially, SustainAI extends beyond technical optimization through a Care by Design lens, framing AI sustainability around relational ethics, regional equity, and ecological stewardship. By combining water monitoring, adaptive accountability, and Care by Design principles, SustainAI provides a practical foundation for integrating ethical care and environmental responsibility into AI infrastructure design and lifecycle management.
Read the full abstract ▾
All authors Farnaz Farid, Tashfia Towkee, Sania Nasreen, Sami bin Azad
Machine Learning
Mechanism-Aware Ensemble Conditioning for Data-Limited Emulation of Extreme Events
Isabella S. Thiel, Juan Bello-Rivas, Yannis G. Kevrekidis et al. (+1 more)
Extreme events in chaotic systems are difficult to learn from short trajectories because they are controlled by transient finite-time instability rather than by frequently observed bulk dynamics. We propose a mechanism-aware conditioning plug-in framework that turns a nudged coarse ensemble into a non-intrusive sensor of local instability geometry. In the small-noise regime, the ensemble covariance aggregates the same finite-time deformation kernels that govern local instability, providing a Jacobian-free proxy for the local amplification structure around a synchronized coarse trajectory. A small FiLM module injects statistics of this ensemble geometry into an otherwise unchanged backbone while leaving the coarse simulator unchanged. We demonstrate this interface in two distinct pipelines: a
Transformer-style residual-
attention corrector for a controlled low-dimensional chaotic system and a probabilistic recurrent STORN corrector for topographic two-layer quasi-geostrophic (QG) flow. In the low-dimensional
benchmark, ensemble covariance directions co-activate with OTD modes and FiLM conditioning improves 99th-percentile exceedance-frequency errors over an identical no-context
Transformer baseline. In QG, a fixed ensemble-conditioned FiLM-STORN model trained on only \(50\) time units substantially improves long-horizon rare-event statistics in the data-limited regime, including density-tail errors, exceedance frequencies, and spatial exceedance-area distributions relative to an unconditioned STORN trained on the same data; on averaged high-threshold exceedance diagnostics, it also outperforms the baseline STORN trained with $20$ times more high-resolution data. These results show that local instability geometry is not merely interpretable post hoc, but an actionable conditioning signal for data-efficient rare-event emulation.
Read the full abstract ▾
All authors Isabella S. Thiel, Juan Bello-Rivas, Yannis G. Kevrekidis, Themistoklis P. Sapsis
Robotics
Anatomy-Aware Dexterity-Driven Design Optimization of Surgical Continuum Robots
Tony Qin, Peter Connor, Khoa Dang et al. (+4 more)
Performing complex medical procedures with continuum
robots requires careful selection of their
geometric design parameters. The
robot should have high dexterity in the specific anatomical environment of its procedure. This work presents a design optimization method that considers both dexterity and anatomy. We introduce the Reachable Volumetric Dexterous Solid Angle (RVDSA) metric as our objective, which measures the ability of a
robot's end effector to reach the points in a goal volume from different directions via collision-free paths from a start configuration. We present a computationally efficient motion planner to compute this objective function for a given robotic design, and we use an asymptotically optimal simulated annealing optimizer to compute an optimized design. We applied our new method to optimize the design of a bimanual dexterous sheaths
robot for performing procedures on cancerous polyps in colon anatomies, achieving a 78% higher RVDSA on average than optimizing for 3D voxel coverage alone.
Read the full abstract ▾
All authors Tony Qin, Peter Connor, Khoa Dang, Carter Hatch, Caleb Rucker, Robert J. Webster III, Ron Alterovitz
Artificial Intelligence
From S3Q Theory to Implementation: Towards an Architecture for Machine Qualia
Tetiana Grinberg, Katrina Schleisman, Patryk Laurent et al. (+6 more)
A key challenge in machine consciousness research is translating theoretical models into computational-level implementations. In this paper, we address this challenge by proposing a five-layer implementation architecture for the S3Q (Simulated, Situated, Structurally Coherent) theory of consciousness. Rather than introducing novel formalisms, the architecture composes published computational primitives into a single pipeline. S3Q identifies three jointly necessary conditions for qualia: (1) grounded sensorimotor situatedness, (2) internal simulation via a world model, and (3) structural coherence between predictions and observations. No existing computational system implements all three simultaneously. We map each S3Q tenet to specific, compatible computational machinery and specify how these components interface within a single representation pipeline that operates on continuous, differentiable, per-object slot vectors, along with a developmental bootstrap sequence and falsifiable predictions for the composed system that no subset of the architecture produces in isolation. The model suggests that a basic sense of "self" develops by linking actions to their outcomes, and that behavior falls into three patterns (hesitation, curiosity, or avoidance) depending on how unexpected an outcome is and whether it is experienced as positive or negative. Each prediction is individually falsifiable, providing the field with a testable framework to advance our understanding of machine consciousness.
Read the full abstract ▾
All authors Tetiana Grinberg, Katrina Schleisman, Patryk Laurent, Bogdan Udrea, Minda Myers, Brian Aufderheide, Luis El Srouji, Doyle Groves, Kevin Schmidt
Data Structures and Algorithms · Cross-listed from math.OC
Optimal Prophet Inequalities for Gain from Trade
Xujin Chen, Xiaodong Hu, Changjun Wang et al. (+1 more)
We initiate the study of prophet trading, an online trading model in which a trader interacts with sellers and buyers who arrive in a uniformly random order and whose prices are drawn independently from a common known distribution. The trader aims to maximize the expected gain from trade (GFT), with performance measured against an omniscient prophet that knows the realized arrival order and all prices in advance. Unlike the classical prophet inequality problem, the trader must make both purchasing and selling decisions while managing the inventory, which makes both the prophet
benchmark and the analysis of online
algorithms substantially more intricate. For arbitrary numbers of buyers and sellers, we propose a simple threshold-based
algorithm and prove a distribution-free competitive ratio of~2, which is the best possible. Our main technical contribution is an exact characterization of the inventory process induced by threshold trading. By expressing the
algorithm's expected GFT in terms of the cumulative holding probability at buyer arrivals, we derive an exact formula for this inventory term, which serves as the foundation of our analysis and yields sharper guarantees in several important special cases. For balanced trading (with $n$ sellers and $n$ buyers), we improve the competitive ratio to $(2n^2-n)/((n+4^{-n}-1)(n+1))$, which is strictly less than 2 for every $n>1$. For the single-seller case, we sharpen the analysis of the fixed-threshold
algorithm to obtain an asymptotic competitive ratio of $2e^2/(e^2+1)\approx1.76$. Furthermore, by exploiting the additional structure of this setting, we design an adaptive-threshold
algorithm whose competitive ratio approaches $e/(e-1)\approx 1.58$. Due to a
symmetry property of our general algorithmic idea, the same $1.76$-competitive guarantee also holds for the single-buyer case.
Read the full abstract ▾
All authors Xujin Chen, Xiaodong Hu, Changjun Wang, Qingjie Ye
Computer Vision
From Mono to Stereo: Accelerating Binocular Gaussian Splatting via Reprojection and Selective Patching
Hongfei Zhu and Ling Zhou
Binocular rendering requires two nearby views of the same scene and therefore repeats substantial visibility and shading work. We present a 2D Gaussian Splatting (2DGS) pipeline that fully renders a dominant-eye RGB image and an alpha-weighted depth proxy, reprojects that image to the affiliated eye, and repairs uncovered pixels. Small interior gaps are interpolated, whereas larger disoccluded regions are identified as regions of interest (ROIs) and selectively re-rendered. The depth proxy reuses the alpha-blending weights computed during dominant-eye rasterization, avoiding a separate depth-rendering pass. An adaptive ROI generator localizes the required updates using reprojected image boundaries and optional connected center-hole detection. On DTU, Tanks and Temples, and MipNeRF-360, the method reduces the measured time of a sequential two-pass binocular reference by 15.5% to 28.8% and peak GPU
memory by 6% to 11%. The corresponding affiliated-eye quality degradation is at most 1.3 dB PSNR, 0.02 SSIM, and 0.02 LPIPS, representing a measurable trade-off that requires application-specific perceptual validation. These results establish a practical efficiency-quality trade-off for controlled static-scene stereo rendering and motivate future evaluation under continuous motion and on physical VR hardware.
Read the full abstract ▾
Computation and Language
Puja Ahmad Habibi, Faiz Assabil Firdaus, Ashvanth S et al. (+3 more)
Multilingual text-
vision embedding models are essential for cross-lingual image-text
retrieval, but Southeast Asian
languages remain poorly supported due to the region's linguistic diversity and limited data and computing resources. In this paper, we introduce SEA-CLIP-Tiny, a compact
multilingual text-
vision embedding model for Southeast Asia with fewer than 50M parameters. Our model adapts a CLIP-KD-style framework to Southeast Asian
multilingual settings through regional data curation and
multilingual teacher guidance. Experiments across seven Southeast Asian
languages show that SEA-CLIP-Tiny achieves the strongest average
retrieval performance among the evaluated student models, reaching 12.9%, 31.5%, and 42.2% at R@1, R@5, and R@10, respectively. Compared with MobileCLIP2, it improves average R@10 by 12.1 points while using 38.4% fewer parameters and lower measured CPU latency. These results highlight the importance of region-aware training for efficient
multilingual text-
vision models in Southeast Asia.
Read the full abstract ▾
All authors Puja Ahmad Habibi, Faiz Assabil Firdaus, Ashvanth S, Ekapol Chuangsuwanich, Pume Tuchinda, Peerat Limkonchotiwat
Computation and Language
Beyond Mean Attention: Diversity-Aware, Layer-Wise Scoring for KV Cache Eviction
Tianfang Xie and Wei Zhu
KV cache eviction methods such as SnapKV and PyramidKV rank
tokens solely by mean
attention over a small observation window. We study a unified score, $\mu_i+\lambda_1\sigma_i+\lambda_2\mathrm{corr}(i,S)$, adding
attention dispersion across window queries and redundancy relative to selected
tokens. For $\lambda_2<0$, the score penalizes similarity to selected
tokens as in maximal marginal relevance (MMR), without extra forward passes. To test whether this relevance-diversity balance should vary with depth, we compare fixed global coefficients with three-segment and quadratic profiles. Only these depth profiles are searched on a development split under a $\sinh$ reparameterization. On all 16 English LongBench
datasets with Mistral-7B at a budget of 64 entries per layer, a single global diversification constant improves 13 of 16
datasets (macro +1.1); the gain holds at budget 32 and narrows at 128. Per-
dataset search finds no detectable layer structure on most
datasets; on passage
retrieval it finds a large one: a mid-layer sign flip that rewards similarity and is worth +9.6 over the baseline at budget 64 and, without re-tuning, +13.2 over the global constant at budget 128. Ablations attribute the gain to the redundancy term; replaying every accepted search state on the held-out test set separates genuine structure from tuning noise.
Read the full abstract ▾
Robotics
Praxis: Distilling Physical Interaction Priors from Egocentric Videos for Generalizable Whole-Body Manipulation
Shuliang He, Ruiyan Xu, Bo Yue et al. (+5 more)
Mobile
humanoid manipulation requires both reaching a usable workspace and preserving precise hand-object interactions as object poses and contact conditions change. Learning these behaviors from limited task-specific data remains challenging. To bridge this gap, we introduce Praxis, a whole-body manipulation framework that combines physical interaction priors from one-shot
egocentric video demonstrations with closed-loop posture calibration and online perception. The framework coordinates three stages:
vision-
language-guided
navigation toward target objects, closed-loop posture calibration to align the arm-hand workspace, and dexterous manipulation with synchronized upper- and lower-body control. Online visual feedback re-grounds demonstrated interaction geometry under new object poses and scene configurations, while tactile feedback adapts hand motions to actual contact conditions. Each manipulation skill is specified by one human demonstration, without task-specific manipulation-policy retraining. Experiments across five long-horizon manipulation tasks demonstrate spatial, visual, and cross-object generalization, as well as recovery from external physical disturbances across all three stages.
Read the full abstract ▾
All authors Shuliang He, Ruiyan Xu, Bo Yue, Hengming Zhang, Huayi Zhou, Shuai Wang, Wei-Shi Zheng, Guiliang Liu
Artificial Intelligence
Learning What to Skip: Counterfactual Credit Assignment for Efficient Multi-Agent LLM Workflows
Jinfeng Xu, Zheyu Chen, Ziyue Peng et al. (+6 more)
Multi-
agent LLM workflows use planning, execution, verification, and summarization to improve task performance, yet the value of each component depends on the state already produced. Executing every component can waste computation or overwrite a correct intermediate answer. We formulate component omission as counterfactual credit assignment: full-workflow logs reveal the executed trajectory's reward, while controlled skip interventions reveal the consequences of omitting a future step. We introduce Learning What to Skip (LW2S), which learns action-specific safety models from these interventions and combines held-out calibration with domain-native guards to select skips. When an early skip is rejected, the controller can continue execution and reconsider a later component. Across mathematical
reasoning, multiple-choice QA, and code generation with two instruction-model families, LW2S reduces recorded
token cost while matching or improving aggregate full-workflow accuracy in the evaluated settings. Scale-up and second-
topology experiments further examine component redundancy, while shared-error cases reveal why agreement alone is insufficient for skip selection. These findings connect efficient workflow execution to learning the conditional utility of individual components.
Read the full abstract ▾
All authors Jinfeng Xu, Zheyu Chen, Ziyue Peng, Zheng Lin, Shuo Yang, Jinze Li, Zheng Xing, Mengran Li, Victor C. M. Leung
Computer Vision
Amplify What You Gaze At: Target Saliency Boosting in Text-to-Image Generation
Shengqi Dang, Zhengxi Yu, Feilin Han et al. (+2 more)
Text-to-image generation has advanced in controlling what, where, and how objects appear, yet how visual
attention is distributed among objects remains largely unexplored. In this paper, we introduce Target Saliency Boosting, a new task aimed at boosting the visual saliency of a specific object during text-to-image generation without requiring any visual priors. Our key insight is that visual saliency is inherently relative: boosting the saliency of a target object also depends on the global saliency distribution across all objects in the scene. Based on this insight, we propose GazeME, a lightweight framework that uses saliency-marked
prompts, inserting learnable marker
tokens around object descriptions to indicate which objects to visually emphasize or suppress. To learn these markers, we construct a saliency-semantics
dataset that associates objects in image–
prompt pairs with object-level saliency scores, and propose Saliency Prior Marker Activation (SPMA), a saliency-aware
stochastic marker activation strategy that exploits relative saliency relationships for robust training. During inference, GazeME automatically inserts appropriate markers into the
prompt, thereby directly enhancing the visual saliency of the target object. Extensive experiments demonstrate that GazeME effectively boosts target saliency while preserving both semantic
alignment and image quality.
Read the full abstract ▾
All authors Shengqi Dang, Zhengxi Yu, Feilin Han, Xingyu Lan, Nan Cao
Machine Learning · Cross-listed from math.OC
TR-SSQP: A Trust-Region Method for Constrained Stochastic Optimization under Heavy-Tailed Noise
Haoxuan Wang, Yuchen Fang and Sen Na
We consider
stochastic nonlinear optimization problems with deterministic equality constraints. While unconstrained
stochastic optimization is well understood, the interplay between optimality and feasibility in the constrained setting poses significant challenges. Moreover, existing theoretical guarantees for constrained
stochastic methods predominantly rely on bounded-variance assumptions, leaving the heavy-tailed noise regime largely unexplored. To address this gap, we propose a novel trust-region method within the
stochastic sequential quadratic programming framework, termed TR-SSQP. Our method employs a normal-tangential decomposition in the step computation to balance optimality and feasibility. In addition, we incorporate a normalization mechanism in the design of the trust-region radius, together with Polyak momentum for gradient estimation, ensuring stable updates without gradient clipping. When the trust-region radius and the momentum parameter decay at appropriate rates, we establish global almost-sure convergence of the method. To the best of our knowledge, this is the first asymptotic convergence result for constrained
stochastic optimization under heavy-tailed noise. We demonstrate the promising performance of the proposed method through extensive numerical experiments, including comparisons among its variants and with existing constrained
stochastic optimization methods.
Read the full abstract ▾
Neural and Evolutionary Computing
Structured Bayesian Modeling of Dynamic Receptive1 Fields in Salamander Retinal Ganglion Cells
Alokesh Manna
Neurons in the visual system are selective for specific spatial and temporal stimulus features, described by their receptive field. Estimating one means a coefficient per pixel per time bin from few trials – a high-dimensional problem requiring regularization. Sparse regularizers such as the LASSO handle the dimension but select pixels independently at each time point, with nothing to keep the region coherent in space or smooth in time; it can fragment or reorganize discontinuously even when the true response evolves smoothly, a failure since this evolving pattern is what a receptive-field estimate should capture. We formulate dynamic receptive-field estimation as a high-dimensional
Bayesian problem: a Poisson model combining a Gaussian Markov random field in space with an autoregressive process in time, so the estimated field is smooth and coherent across space and time. On recordings from $155$ salamander retinal ganglion
cells, fitting this model independently per
neuron recovers a coherent surface, where a pixel-level Poisson-LASSO comparison instead returns a fragmented one. Summarizing each
neuron's surface by its space-averaged temporal response and clustering these curves with a model-based functional-clustering procedure, BIC selects three balanced temporal-response phenotypes ($85$, $32$, $38$
neurons), against a degenerate grouping from clustering the raw surfaces. A simulation study with known ground truth confirms the same pattern, with the model beating an unregularized Poisson GLM, LASSO, and the elastic net on recovery and estimation accuracy, though LASSO controls false positives better. The per-
neuron field identification, its contrast with LASSO, and the functional-clustering population typing constitute this paper's contribution.
Read the full abstract ▾
Cryptography and Security
Input-Layer Starvation: Why Per-Layer Pruning Breaks IoT Intrusion Detectors
Md Anas Biswas
Intrusion detectors for small Internet-of-Things (IoT) devices are usually compressed by
pruning and judged by overall accuracy. We show that this hides a severe class-level failure, find its cause, and give low-overhead prevention and repair. On CICIoT2023, a two-layer convolutional detector pruned with uniform layer-wise magnitude
pruning at 80% sparsity loses 16 points of accuracy but half of its macro-F1, the mean per-class F1 (0.542 to 0.271 over five independently trained models); 17 of 34 classes are materially damaged. Remaining weight count does not explain it: a perceptron and a
transformer pruned to the same or fewer weights lose at most 0.096. The first layer does. It has 192 weights; uniform
pruning leaves 38, 46% of its 64 filters lose every input weight, and fine-tuning under that starvation leaves the running means of the first normalisation layer displaced by up to 0.8 standard deviations in a few surviving channels, on which the deployed model collapses. Protecting those 192 weights, or
pruning globally at the same sparsity, prevents the collapse (loss 0.013); recomputing the normalisation statistics on unlabelled training data, with no weight changed, repairs it (loss 0.039) and returns the false-alert rate to 33% (dense 29%). Damage shows a strong increasing dose-response in first-layer sparsity, starving a perceptron's input layer reproduces the collapse, and the pattern holds on TON_IoT. The failure is misattribution and false alerts, not silent evasion: on validation-selected blind spots, uniformly pruned detectors misattribute 72% of the traffic, against 50% with the first layer protected and 47% for the dense model.
Read the full abstract ▾
Computer Vision
Learning Polarization Image Restoration with General Restoration Priors
Chenggong Li, Jinhao Liu, Caiyun Wu et al. (+3 more)
Polarization imaging captures distinctive surface and
geometric cues that benefit a wide range of
vision tasks. However, real-world polarization acquisition is often affected by multiple coupled degradations, making image restoration essential for practical polarization
vision. Existing methods are largely tailored to specific degradations and remain constrained by the limited scale and quality of polarization data. To address these limitations, we develop an all-in-one polarization restoration framework for diverse and composite degradations. We first study the impact of different polarization representations on restoration performance and identify the normalized Stokes representation as an effective choice for separating intensity and polarization information. Accordingly, we devise a dual-branch architecture that separates intensity and polarization modeling. To overcome the limitations of polarization-specific training, the intensity branch leverages pretrained general restoration priors and a mixture-of-experts extension for composite degradations, while its restoration knowledge is adaptively distilled into the symmetric polarization branch via a cross-domain feature transform. In addition, we establish a composite-degradation polarization
benchmark to support all-in-one restoration research. Extensive experiments on public
datasets and our proposed
benchmark demonstrate the effectiveness of the proposed method.
Read the full abstract ▾
All authors Chenggong Li, Jinhao Liu, Caiyun Wu, Yidong Luo, Junchao Zhang, Degui Yang
Artificial Intelligence
Analyzing and Mitigating Cost-Inefficient Behaviors in Coding Agents
Yiran Hu, Nan Jiang, Shanchao Liang et al. (+3 more)
Although effective, coding
agents often incur substantial monetary costs. Their recurring cost-inefficient behaviors remain underexplored. We conduct the first study of behavioral cost inefficiencies in coding
agents, analyzing 1,200 trajectories from Claude Code and Mini-SWE-
Agent across four configurations on SWE-bench Verified. We identify three cost-inefficient behaviors: subsumed
retrieval, similar script generation, and test re-execution. We then evaluate three mitigation strategies: structure-aware
retrieval,
agent-synthesized skills, and developer-designed skills, over 10k trajectories on held-out SWE-bench Verified and Pro tasks. Our main findings are: (1) The three behaviors affect 79.00%–98.00% of coding tasks and account for up to 22.75% of task cost. (2) Structure-aware
retrieval can introduce
retrieval overhead and alter
agent delegation, causing inconsistent improvements in
retrieval efficiency and cost increases of up to 28.14%. (3)
Agent-synthesized skills tend to produce low-level, trace-specific guidance, limiting their effectiveness and generality. (4) In contrast, developer-designed skills provide high-level, trace-agnostic guidance, reducing cost by up to 41.73%, roughly twice the maximum gain from
agent-synthesized skills.
Read the full abstract ▾
All authors Yiran Hu, Nan Jiang, Shanchao Liang, Anik Dey, Yi Wu, Lin Tan
Computer Vision
EviDETR: Preserving Query-Relevant Temporal Evidence for Moment Retrieval and Highlight Detection
Haoran Sun, Yufan Li, Qichen Zhang et al. (+2 more)
Joint
video moment
retrieval and highlight detection requires identifying query-relevant temporal segments while estimating clip-level saliency, yet DETR-style pipelines do not explicitly preserve query-relevant evidence throughout encoding, decoding, and cross-task prediction. We propose EviDETR, an evidence-preserving framework with three components. Semantic-aware Feature Reweighting (SFR) enhances query-relevant clip representations through saliency estimation and cross-modal interaction. A Temporal Top-2 Mixture-of-Experts (TTop2MoE) decoder performs query-adaptive refinement via sparse expert routing. MR-to-HD (MR2HD) fusion transfers span-level
retrieval evidence to clip-level highlight prediction through confidence-weighted multi-scale aggregation. Using CLIP+SlowFast features, EviDETR achieves 69.29 R1@0.5, 54.77 R1@0.7, and 48.41 Avg. mAP for moment
retrieval on QVHighlights, together with 41.83 HD-mAP and 68.33 HIT@1. Strong results on TACoS and Charades-STA further demonstrate cross-
dataset transferability.
Read the full abstract ▾
All authors Haoran Sun, Yufan Li, Qichen Zhang, Haoran Zhao, Shuqi Wang
Computer Vision
TrafficImag: A Benchmark for Counterfactual Roadside Traffic Video Generation
Xiangyu Li, Tianyi Wang, Zhihao Dou et al. (+2 more)
Existing roadside traffic
datasets support perception,
forecasting, and visual question answering, but they do not evaluate counterfactual
video generation, in which a selected actor is modified and the generated future should remain consistent with road
topology and unrelated traffic. We introduce TrafficImag, the first
benchmark for counterfactual roadside traffic
video generation. TrafficImag combines a large-scale roadside
dataset (9,022 annotated images, 7,043 deduplicated
video clips, and 31,145 actor-centered history-future samples) with an executable protocol that supports behavior
reasoning, intervention-aware image editing, and conditional
video generation. Each intervention is represented as an actor-level program describing the target actor, intended behavior, legal route, interaction order, and temporal constraints, enabling a unified evaluation interface across heterogeneous foundation models. TrafficImag evaluates four complementary validity dimensions: initial-state correctness, route and behavior validity, interaction consistency, and non-target preservation, and considers an end-to-end counterfactual successful only when all four are satisfied. Across state-of-the-art foundation models, the strongest reasoner reaches 80.4% macro F1, the complete condition interface raises end-to-end success from 23.3% to 55.0% for the best generator. Oracle studies further show that conditional
video execution is the primary remaining bottleneck. TrafficImag provides a reproducible
benchmark for evaluating and diagnosing counterfactual traffic
video generation beyond perceptual
video quality.
Read the full abstract ▾
All authors Xiangyu Li, Tianyi Wang, Zhihao Dou, Christian Claudel, Zhaomiao Guo
Machine Learning
When 10,000 Windows Are Not 10,000 Tests: Auditing Statistical Confidence in Sliding-Window Time-Series Classification
Xinze Shi, Litian Zhang and Binrui Shi
Sliding-window classifiers are often evaluated on thousands of overlapping test windows, even though neighboring predictions share observations and remain nested within recordings and subjects. Subject-disjoint evaluation prevents one form of leakage but does not make those test windows independent. We present a practical audit that maps three claims - performance on observed recordings, future recordings from observed subjects, and unseen subjects - to explicit aggregation rules and established dependence-robust inference. At 75% overlap, controlled simulations give 16.9% Type-I error for IID observed-record inference and 7.2% for session-centered Bartlett-HAC: a substantial improvement with residual miscalibration. Audits of frozen WISDM and HARTH predictions show that nearly fourfold growth in test rows yields only 1.75-1.94-fold variance-equivalent information growth. At that overlap, fixed-record paired Accuracy-difference intervals are 1.22-1.66 times the IID widths; this inflation is not universal at zero overlap. On HARTH, paired Accuracy-difference intervals include zero across three overlap settings, whereas Macro-F1 favors MiniROCKET. Independent recomputation, common-session checks, class-level results, and separately seeded calibration make the audit's scope and limitations inspectable. The resulting workflow distinguishes additional predictions from additional independent evidence.
Read the full abstract ▾
Cryptography and Security
Werracle: Sub-Cent Intra-Block AI Reflex Oracles and Flash-Loan Circuit Breakers for EVM Smart Contracts
Volkan Dağl{\i}, Zerrin Dağl{\i} and Dağhan Dağl{\i}
Contemporary on-chain artificial intelligence (AI) encounters an intractable Von Neumann
memory and latency wall. Storing static floating-point neural weight
matrices inside Ethereum Virtual Machine (EVM) storage costs millions of gas, rendering direct on-chain inference impossible. While Zero-Knowledge Machine Learning (ZK-ML) offloads
matrix tensor multiplications to off-chain provers, it introduces fatal constraints: 10 to 300 seconds of SNARK proving latency and 250,000 to 500,000 gas per proof verification. Because decentralized finance (DeFi) exploits - such as uncollateralized flash-loan attacks, predatory sandwich MEV, and toxic loss-versus-rebalancing (LVR) flow - occur atomically inside a single block, ZK-ML oracles cannot react in time. Here, we present Werracle, a production-grade, zero-storage on-chain AI decision oracle fitting inside a single 32-byte EVM storage slot (bytes32). Leveraging foundational procedural Mandelbrot escape dynamics (z_{n+1} = z_n^2 + c) established by Dagli et al. (arXiv:2609.25498), Werracle derives continuous non-linear decision hyperplanes from a 24-byte coordinate triplet Theta = (c_x, c_y, zoom). Implemented in pure Solidity bytecode using fixed-point Q16.16 arithmetic (WerrMath.sol), Werracle evaluates a 16-point Pareto micro-grid in only 21,438 gas (under 0.0005 USD on Layer-2 rollups like Base and Arbitrum) with sub-millisecond execution latency. We demonstrate real-world DeFi efficacy via WerracleFeeHook.sol, a Uniswap v4 dynamic swap fee governor that measures orderbook
turbulence on-the-fly and atomically adjusts liquidity provider fees between 0.05% and 0.50%. The protocol is formally verified against a 1,000-test cryptographically sealed deterministic verification suite (100.0% pass rate) with telemetry permanently disabled, operating live on a dedicated EVM devnet sandbox (Chain ID 4242).
Read the full abstract ▾
Machine Learning
NEMSim: Learning Control-Conditioned Multi-Event Physical Dynamics via Executable Event-Mechanism Priors
Junsong Yu, Junjie Xie, Pengwei Liu et al. (+1 more)
High-fidelity simulation of control-conditioned multi-event physical systems is computationally expensive, especially across broad control spaces and long trajectories. In these systems, macroscopic
evolution emerges from localized discrete events whose intensities and effects depend on process controls and evolving local states, while the available system knowledge is typically expressed as event-attribute descriptions. Purely data-driven surrogates must infer these event effects from limited trajectory coverage, which can hinder generalization to unseen control regimes. Physics-guided methods instead primarily build on equation-level constraints or differentiable solvers rather than discrete event-rule priors. We therefore propose NEMSim (Neural Event-Mechanism Simulator), which compiles predefined event-attribute descriptions into an executable transition structure linking control-dependent event intensities, prior-guided mechanism attribution, and state-dependent responses. To enable evaluation of control-conditioned multi-event dynamics with explicit system knowledge, we construct a 3D KMC-based
benchmark pairing high-fidelity trajectories with explicit event rules, standardized splits, and evaluation protocols. Across three settings, NEMSim reduces Avg. RMSE by 58.9%-81.3% relative to the strongest baseline in each setting. It also remains best in the data-efficiency study with training-data fractions down to 10%. Mechanism analyses further show that these gains arise from executable rule integration rather than prior access or architecture alone.
Read the full abstract ▾
All authors Junsong Yu, Junjie Xie, Pengwei Liu, Dong Ni
Information Retrieval
RecToolBench: Benchmarking Recommendation-Specific Tool Orchestration under Fuzzy User Intent
Xiao Chen, Yicheng Zhao, Yingying Wu et al. (+4 more)
Recent advances in agentic recommender systems are shifting recommender systems from passive filtering engines to instruction-following
agents that use external tools to resolve user intent. However, existing
benchmarks often assume explicit user intent, simplified tool environments, or isolated function calls, leaving realistic tool orchestration for recommendation underexplored. To bridge this gap, we propose RecToolBench, a Model Context Protocol (MCP)-based
benchmark for evaluating tool-using recommender
agents under fuzzy user instructions. RecToolBench contains more than 1,200 executable tasks across three recommendation domains, 13 MCP servers, and 32 tools, spanning single-tool calls, parallel tool calls, sequential tool chains, and hybrid tool orchestration. We construct RecToolBench with a scalable synthesize–fuzzify–judge pipeline that generates executable fuzzy recommendation tasks, and evaluates
agent trajectories using rule-based execution checks and rubric-based LLM evaluation. Experiments on representative LLMs show that syntactically valid tool calls do not guarantee successful recommendations. Models struggle with semantic parameter grounding, multi-step evidence integration, and grounded final recommendations, especially as orchestration complexity increases. Our results identify tool orchestration under fuzzy user intent as a major bottleneck for agentic recommender systems. Our data and code are available at https://github.com/ShawnChenn/RecToolBench.
Read the full abstract ▾
All authors Xiao Chen, Yicheng Zhao, Yingying Wu, Zhendong Chu, Changyi Ma, Qingsong Wen, Xuan Song
Computation and Language
Words Speak Louder Than Order: A Behavioral Evaluation of Gemma 4
Amanda Fitch
When a
language model receives two conflicting documents as input, how does it decide which one to prioritize? Does it rely on how the sources are framed or the presentation order of the documents? We evaluated this behavior on Google's pre-trained Gemma 4-e4b model across a targeted behavioral suite (n = 13 items, 784 forward passes in short, single-turn contexts) using a completely counterbalanced experimental design. This setup allowed us to mathematically isolate the specific effects of source framing and reading position, while ensuring the model's natural vocabulary biases were canceled out. Across ten test conditions, we discovered the following: 1. Source framing heavily overpowers reading position. When directly competing, the semantic framing of a source (such as presenting it as an official guideline or a fresh update) had a significantly stronger impact on the model's final answer than the presentation order of the document. 2. The model favors the first document it reads, but this bias is highly variable. While the model consistently demonstrated a primacy effect (preferring the first document presented), the actual strength of this bias fluctuated by at least a factor of 5 based solely on the surface wording. 3. Overall structural repetition, not short copy-cues, drives positional bias. The model's preference for the first document is not a mechanical reaction to short, repetitive trigger phrases, such as "is [Answer]". However, the primacy effect does increase significantly when the two competing documents are structurally identical, using word-for-word verbatim templates. Introducing variation in the overall wording between the two sources reduces this positional bias.
Read the full abstract ▾
Robotics
RoboMonitor: Label-Efficient Runtime Monitoring of Robot Task Execution via Predictive Representation Learning
Abhiroop Ajith, Gokul Narayanan, Kyle Coelho et al. (+7 more)
Learned
robot policies produce actions, but their outputs alone do not establish whether execution is progressing as intended.
Robot execution monitoring requires identifying the current execution phase, detecting failures, and recognizing task completion from observations available during execution. Training such monitors requires annotations that are scarce in
datasets collected for
robot-policy learning. We present RoboMonitor, a label-efficient
vision–
language execution monitor that learns from these
datasets before introducing monitoring supervision. We pre-train on 25 hours of multi-camera trajectories spanning 12 manipulation tasks and two
robot embodiments, using action-conditioned future-feature prediction, inverse dynamics, and masked-present prediction. We then transfer the learned visual and context encoders to a causal monitor and apply temporal supervised fine-tuning (Temporal SFT), which combines supervision throughout each observation window with consistency objectives within and across overlapping windows. At deployment, RoboMonitor requires only the task instruction and camera observations. On a four-task monitoring
benchmark, RoboMonitor trained with 52 labeled episodes achieves 93.1% mean phase accuracy and 85.9% macro recall over two fine-tuning seeds, exceeding Qwen3-VL and Robometer trained with the same monitoring supervision. Its phase accuracy also exceeds that of both Qwen3-VL and Robometer trained with 100 episodes. A Qwen3-VL ablation shows that Temporal SFT reduces mean spurious phase switching from 15.23% to 4.95%. In closed-loop deployment, the integrated system completes 39 of 40 simulated Toolbox Sorting trials and 35 of 40 real-world Reel Packing trials, with no false recovery triggers observed.
Read the full abstract ▾
All authors Abhiroop Ajith, Gokul Narayanan, Kyle Coelho, Tingji Zhao, Yash Shahapurkar, Brian Zhu, Melih Erdogan, Ted Krubasik, Constantinos Chamzas, Eugen Solowjow
Artificial Intelligence
CRC-Router: Risk-Constrained Routing for Medical Agentic AI Systems
Xueyang Li, Mingze Jiang, Gelei Xu et al. (+5 more)
Agentic AI systems are increasingly being explored in medical imaging to improve throughput and reduce clinician workload; however, safe deployment remains challenging because autonomous errors may propagate into downstream clinical decisions. A central requirement is therefore not only strong predictive performance, but also a reliable routing mechanism that determines when the system should proceed autonomously and when a case should be escalated for further review. To address this gap, we propose CRC-Router, a risk-constrained, uncertainty-aware routing module that is applicable to both conventional medical prediction models and agentic medical AI systems. CRC-Router combines multiple complementary uncertainty signals with the predictive score to construct a per-finding routing feature vector, maps this vector to an estimated wrong-accept risk using a lightweight per-finding risk model, and then applies Conformal Risk Control (CRC) to calibrate acceptance thresholds under a user-specified risk target. Instantiated on chest X-ray multi-finding triage using the NIH ChestX-ray14
dataset, CRC-Router achieves the strongest empirical risk–coverage trade-off among the evaluated baselines, both as a standalone routing layer and as a plug-in module integrated with the state-of-the-art MedRAX
agent. These results demonstrate both the effectiveness of CRC-Router in selective medical automation and its modular, model-agnostic compatibility with existing predictive and agentic medical pipelines. Code is publicly available at https://github.com/XLIAaron/CRC-Router
Read the full abstract ▾
All authors Xueyang Li, Mingze Jiang, Gelei Xu, Jun Xia, Ching-Hao Chiu, Mengzhao Jia, Danny Z. Chen, Yiyu Shi
Machine Learning · Cross-listed from stat.ML
Parameter Estimation for Unnormalized Discrete Models via Empirically Localized Deformed Bregman Divergence
Takashi Takenouchi
Estimation of parameter of probabilistic models is an important task in the field of machine learning.For models of discrete variables, calculation of the normalization constant of model is sometimes difficult and a lot of researches have been done to avoid the calculation of the normalization constant. In this paper, we tackle with the difficulty by combining a technique of empirical localization and a deformed Bregman divergence.The technique of empirical localization makes it possible to drastically reduce computational cost of the calculation of the normalization constant, and in addition, appropriate choice of the deformation for the Bregman divergence can invest the proposed
estimator with various kinds of favorable statistical properties, such as efficiency or robustness against outlier noise.
Read the full abstract ▾