Peer Revenue Past citations are no guarantee of future returns

Papers

Fresh from arXiv, typeset properly. Highlighted words trade on the market.

All of arXiv

Tuesday 29 September

Graphics

StereoSplat: Metric-Scale Novel View Synthesis via Stereo-Grounded Gaussian Splatting

Vladimir Yugay, Denis Rozumny, Theo Gevers et al. (+3 more)

We present StereoSplat, a feed-forward 3D Gaussian Splatting architecture designed explicitly for stereo videos to achieve reliable, metric-scale novel-view synthesis. Unlike monocular approaches that neglect the nature of binocular pairs, StereoSplat adopts a native stereo architecture that extracts dense multi-scale latent features and disparity from a foundation stereo backbone and feeds them into a dedicated Gaussian decoder. Our decoder utilizes cross-view feature fusion and gated depth refinement to directly translate these rich representations into per-pixel 3D Gaussians. To resolve the high redundancy of per-pixel predictions across overlapping views, we propose a learnable depth-adaptive aggregation mechanism that clusters and aggregates primitives in inverse-depth space while preserving fine-grained details. To support training and generalization, we introduce XRStereo, a large-scale synthetic dataset of stereo video featuring various rig configurations tailored to match the physical hardware of real-world platforms. Trained exclusively on synthetic data and evaluated across challenging benchmarks, StereoSplat yields substantial improvements in the depth accuracy of rendered novel views over established baselines while maintaining high-fidelity novel view synthesis. The model also transfers zero-shot to real-world stereo video, with applications in mixed reality, autonomous driving, and robotics.
Read the full abstract

All authors Vladimir Yugay, Denis Rozumny, Theo Gevers, Elias Vansteenkiste, Martin R. Oswald, Diogo C. Luvizon

Image and Video Processing

ContextTom: Training-Free Video VLM Acceleration with Early Spatial Context

Yuqi Li, Neil Rodrigues, Xianglong Wang et al. (+8 more)

Video vision-language models process thousands of visual tokens before producing an answer. Reducing these tokens early saves computation, but also determines which evidence reaches the language model. We introduce ContextTom, a training-free framework that separates the timing of temporal and spatial compression. Its central idea is to compress time before vision encoding while preserving spatial coverage through early multimodal processing. A fixed-budget temporal partition produces representative medoid anchors, supplemented with bounded local detail from neighboring observations. The anchors retain their complete spatial grids through a short decoder prefix, allowing question tokens to access the visual evidence and completing Qwen3-VL's multi-level visual injections. ContextTom then selects spatial representatives using query attention and agreement across visual feature levels, and continues directly from their computed states. This schedule reduces vision computation and later decoder workload while reusing the prefix. On Qwen3-VL-8B, ContextTom achieves 76.22% accuracy on Video-MME Short with a mean time-to-first-token (TTFT) of 123.5 ms, yielding a 2.77x speedup over full-input inference. It matches the full-input accuracy of 72.20% on EgoSchema with a 2.82x speedup and achieves a 5.54x speedup on LongVideoBench at 59.24% accuracy.
Read the full abstract

All authors Yuqi Li, Neil Rodrigues, Xianglong Wang, Junming Liu, Yi Xiao, Weilun Feng, Chuangguang Yang, Yingli Tian, Zhongwei Cheng, Wei Li, Lin Chen

Image and Video Processing

TeQCo: Temporal Quota Consistency for Training-Free Video Token Compression

Yuqi Li, Xianglong Wang, Neil Rodrigues et al. (+8 more)

Video token compression must control both temporal coverage and task relevance, but sequential stages can conflict: a content-driven allocation stage may be overwritten by a global ranking that removes entire temporal positions. We identify this as an allocation conflict and propose TeQCo, a training-free framework that resolves it through temporal quota consistency. TeQCo allocates candidate capacity from first-order changes in normalized frame representations and aggregates all tokens within each frame into a compact candidate set. Candidates are then scored by prior-corrected task attention and selected within integer frame quotas inherited from the first-stage counts. Content variation determines temporal capacity; question relevance determines which candidates fill it. This design guarantees an exact token budget and a per-frame coverage floor whenever feasible. On the 2,700-question Video-MME benchmark with Qwen3-VL-8B, TeQCo achieves 68.52% accuracy at 510 ms TTFT, a 32.9% TTFT reduction with a 1.00-percentage-point accuracy decrease.
Read the full abstract

All authors Yuqi Li, Xianglong Wang, Neil Rodrigues, Yiru Fang, Weilun Feng, Chuanyue Yan, Chuangguang Yang, Yingli Tian, Zhongwei Cheng, Wei Li, Lin Chen

Quantitative Methods

GoCo: structure-guided conformal calibration for error-controlled Gene Ontology annotation release

Chong Wang, Yongzhao Shao and Peng Liu

Computational gene-function prediction generates annotations at a scale that experimental characterization cannot match, yet substantial errors remain even among leading methods. Explicit error-controlled calibration for Gene Ontology (GO) prediction remains largely undeveloped. We introduce GoCo, a structure-guided framework that calibrates how scores from an existing predictor are converted into released annotations. GoCo certifies a global threshold for a GO-hierarchy-aware gene-level false discovery proportion (FDP), then constructs a nested release path under the same asymptotic risk-control guarantee. At the primary operating point (alpha=0.10, delta=0.50), GoCo-M, developed on Wainberg co-essentiality modules and applied without retuning to three independent studies with the same shared-evidence structure, kept mean held-out gene-level FDP at or below target while releasing 6.3-17.6% more reference-supported GO terms than Multilabel. For gene-specific neighbourhoods, GoCo-N orders individual calls. Developed on FunMap and validated without retuning on the STRING v12.0 experiments-only network, GoCo-N released 33.8% and 36.4% more reference-supported GO terms than Multilabel on the same refined score grid in FunMap and STRING, respectively, while keeping mean held-out FDP below target. The same pattern held under the stricter delta=0.10 setting. Thus, predictor-native biological structure can be reused at calibration, not only prediction, to release more supported annotations at a chosen gene-level error target without retraining the predictor.
Read the full abstract

Machine Learning (Statistics)

Autoregressive Physics-Informed Neural Operator Surrogates and Joint 4-D Seismic-Production Bayesian History Matching

Clement Etienam, David Blom, Hari Pattathil et al. (+7 more)

We present a surrogate-accelerated Bayesian history-matching framework, demonstrated on a realistic synthetic model ($N=100{,}188$ cells). The forward map $\mathcal{G}$ is replaced by a Fourier neural operator $\mathcal{G}_\theta$ trained in a closed loop, $\hat{x}_{n+1}=\mathcal{G}_\theta(u,\hat{x}_n)$, with the discrete black-oil residual $R(x_{n+1},x_n)$ as a physics-informed neural operator (PINO) penalty, truncated backpropagation and noise injection. We assimilate production data and 4-D seismic using adaptive regularised ensemble Kalman inversion (aREKI), and synthesise $\Delta V_p$ inside the rollout via a closed-form Gassmann transform of the surrogate, under a two-stage schedule (aREKI on production, then an ensemble smoother with multiple data assimilation, ES-MDA, on both). To temper the ill-posedness, we invert $(\log K,\phi)$ not in $\mathbb{R}^{2N}$, where $N_e\ll 2N$ leaves a rank-deficient covariance and a null space the data never inform, but on a chart $u=\Psi(\tilde m)$, $\tilde m\in\mathbb{R}^{d}$, $d\ll 2N$, given by a Parseval-exact truncated cosine transform or a variational auto-encoder decoder. The ensemble then spans its own search space; the directions the data cannot constrain are cut to those the chart can express, and every member decodes to a geologically plausible field. For the rollout we prove an exposure bound $W_1\le\sum_j L^{\,n-1-j}\mathbb{E}e_j$, a physics-penalty contraction $\|D_x\mathcal{G}_\theta\|\le\alpha<1$ under a small residual defect, and an $\mathcal{O}(\rho^K)$ truncation bias. A Loewner-order inequality $\mathcal{I}_p\preceq\mathcal{I}_p+\mathcal{I}_s$ explains why joint assimilation is no less informative. On held-out data, $\mathcal{G}_\theta$ attains $R^2>0.999$ on pressure and saturation and rolls out in $0.579$ s, a $\sim2500\times$ speed-up, bringing an $N_e=190$-member, $N_a=10$-iteration joint inversion within one GPU-hour.
Read the full abstract

All authors Clement Etienam, David Blom, Hari Pattathil, Tsubasa Onishi, Harpreet Sethi, Lalson Vincent, Suraj Pawar, Kishan Ramesh Kumar, Pandu Devarakota, Faruk O. Alpak

Instrumentation and Detectors

Background-Limited Silicon Telescope Methodology for Weak Internal Pair Creation Transition in Low-Energy Deuteron-Deuteron Reactions

Gokul Das Haridas, K. Czerski, S. Thulichery et al. (+4 more)

A background-constrained silicon-telescope methodology has been developed to investigate recently observed internal electron-positron pair creation in low-energy deuteron-deuteron fusion. The decay of the near-threshold $0^+$ resonance in $^4$He produced in DD fusion results in an $e^-e^+$ pair sharing a total energy of 22.84 MeV. These high-energy leptons traverse thin silicon detectors and deposit only part of their kinetic energy. The resulting partial-absorption peak structure overlaps with the natural-radiation background of cosmic-ray secondaries and terrestrial gamma rays. The silicon detector telescope used in the present experiments is characterised against this background through a component-by-component model that combines a GEANT4 cosmic-ray simulation, a large-volume NaI(Tl)-constrained terrestrial-gamma propagation, and a beam-correlated neutron response. Long-duration measurements in multiple orientations and shielding configurations are used to quantify the run-to-run variability of the background and to translate it into an explicit systematic envelope on the extracted signal. The framework is then applied to the beam-on singles spectrum and the two-dimensional coincidence response, yielding a quantitative branching-ratio measurement under background-limited conditions. The methodology is directly transferable to other weak-channel searches in surface laboratories where continuum-like signals overlap with natural-radiation backgrounds.
Read the full abstract

All authors Gokul Das Haridas, K. Czerski, S. Thulichery, R. Dubey, M. Valat, N. Targosz-Ślęczka, A. Kowalska

Digital Libraries

MultiphaseHUB for Evidence-Grounded Metadata Curation and Task-Aware Compression of Multiphase Data

Yingyan Zeng, J.P. Panda, Avranshu Mahanty et al. (+3 more)

Multiphase transport experiments and simulations generate high-dimensional data whose scientific value depends on the physical conditions, sensing configuration, calibration, synchronization, uncertainty, and provenance accompanying the raw signals. These data are difficult to reuse when experimental context is scattered across publications and repositories, while large measurement volumes increase the cost of transfer and analysis. In this work, we introduce MultiphaseHUB as a community infrastructure and an integrated framework for organizing, discovering, and reusing multiphase transport data. The infrastructure connects externally hosted datasets with modality-specific metadata, publications, analysis tools, derived features, source repository links, and boundaries for reuse. Within this framework, we develop two complementary components: literature analysis and data curation, comprising Large Language Model (LLM)-assisted metadata extraction and an agentic literature-analyzer for quantitative values from figures; and modality-specific scientific data compression guided by the quantities of interest needed for downstream analysis. These components address the effort required to interpret heterogeneous sources and the cost of accessing useful information from high-dimensional measurements. Public multiphase datasets provide seed resources for illustrating the framework and its workflows. Building on these components, we outline a research roadmap encompassing cross-facility harmonization, multimodal alignment, task-aware retrieval and dataset valuation, and conditional reconstruction of missing modalities. MultiphaseHUB provides a foundation for connecting distributed data resources to physically meaningful comparison and cross-study scientific discovery.
Read the full abstract

All authors Yingyan Zeng, J.P. Panda, Avranshu Mahanty, Han Hu, Depeng Xu, Ying Sun

Number Theory

Galois Groups of Shifted Exponential Polynomials

Shachar Weinbaum

Consider the shifted truncations of the exponential series and their Galois groups: $$F_{n,a}(x) := \sum_{j=0}^{n}\frac{x^j}{(a+j)!}\qquad G_{n,a}:= \text{Gal}(F_{n,a}/\mathbb{Q}).$$ In this paper we prove that for every fixed integer $a>0$, the set of $n$ for which $G_{n,a}=S_n$ has natural density one, thus answering a question of Katz and Rivin.
Read the full abstract

Computer Vision

Instance-Specific Classifier-Free Guidance for Text-to-Image Diffusion/Flow-Based Editing

Wajeeh Atrash and Tom Tirer

In recent years, a variety of prompt-based image editing methods have been developed based on text-to-image (T2I) diffusion/flow models. Image editing introduces an inherent trade-off between adhering to the original source image and realizing the change specified by the target prompt, which are typically measured by the LPIPS and CLIP-T metrics, respectively. Intuitively, this trade-off can be controlled by the classifier-free guidance (CFG) scale. Most existing editing methods, though, use a fixed CFG scale, ignoring that different edits require varying levels of modification. In this paper, we first explore the potential benefits of using an instance-specific CFG by exhaustively re-running prominent editing methods with a wide range of CFG scale values on benchmark datasets. We show that instance-specific setting can significantly improve LPIPS without compromising CLIP-T. Yet, tuning based on repeatedly executing an editing pipeline is inefficient. To prevent slow inference, we train a light-weight neural network that predicts the metrics of the underlying editing method for a given edit instance and CFG scale. At inference time, these predictions enable fast selection of an instance-specific CFG scale. Experiments across multiple editing methods and benchmark settings show the performance advantage of our approach over the baseline methods.
Read the full abstract

Computer Vision

LVMH: A Meta-Optimization Harness for Long-Video Agent Memory

Liwei Che, Benlin Liu, Dai Li et al. (+7 more)

Long-video agents must map hours or days of multimodal evidence into a bounded context while respecting token and latency budgets, making memory design a context-management challenge. Existing memory systems largely rely on hand-designed policies, leaving open how to jointly optimize memory design for performance and efficiency. We propose Long Video Meta-memory Harness (LVMH), an automated multi-agent framework that formulates memory-policy development as multi-objective code search around a fixed answer model. To guard against self-certification and development-set overfitting, LVMH separates implementation from independent review and enforces protected observation boundaries. Persistent meta-memory records past proposals, traces, costs, and failures to guide subsequent policy revisions. Through this harness, we discover Self-Evolving Evidence Memory (SEEM), a "text-first, vision-second" policy that answers from compact structured event memory and evidence specialists, consulting localized frames through a selective visual gate. The policy evolved on EgoLifeQA generalizes to unseen benchmarks, outperforming Meta-Harness on both Ego-R1 Bench and Video-MME (L) with GPT-5 mini. Across the three benchmarks, SEEM with GPT-5 achieves 65.7% average accuracy, surpassing the previous state of the art by 7.7 percentage points with approximately 32x lower average evaluation token use and 91x shorter average response time.
Read the full abstract

All authors Liwei Che, Benlin Liu, Dai Li, Xiangyan Li, Zijian Wu, Changjiang Li, Minghao Guo, Chengzhi Mao, Vladimir Pavlovic, Ranjay Krishna

Computer Vision

AI-Experiment: an augmented reality art project co-created with artificial intelligence

Bernhard Egger and Hans Furer

We describe the creation of a physical artwork that was performed in synergy between an artist, a computer scientist and generative AI tools. A latent diffusion model was finetuned on photographs of the artwork of the specific artist and the generative model then generated synthetic artworks in a similar style. From the generated artworks a subset was selected to be painted again with acrylic on canvas by the original artist. In addition to the physical artifact an augmented reality component was added which brings the artwork to life with a set of generative video models. Together with this paper we release part of the artwork (training data), the code that was deployed to generate the artwork as well as the augmented reality experience for arts, research and education under https://github.com/BernhardEgger/ARTimate
Read the full abstract

Computer Vision

Rethinking weakly supervised localization on chest radiographs: position nulls, protocol dependence, and PACE

Shixin Qiu

Weakly supervised localization on chest radiographs is reported as a single overlap accuracy, and those numbers are not comparable across papers. We measure what one contains. Against position-null controls that keep a readout's own box and move only its position, class activation mapping and its gradient-weighted variant beat the null on two to four of seven annotated findings on ChestX-ray14 and two of eight on CheXlocalize. The null is beatable: three board-certified radiologists clear it on four to seven. Three rarely stated choices each move a result by more than most reported method effects: the results regime, the extraction threshold, and the mask-to-box rule, whose cost is predicted by how fragmented the thresholded mask is. Predicted box area alone reverses a paired comparison. These measurements produced PACE, for population anomaly and class evidence, which multiplies the finding identity from the label-trained head by the spatial evidence from a frozen radiograph backbone that never sees a pathology label. It is the case study that made the protocol dependence visible, and we report its costs beside its gain: in an exploratory matched-area analysis it improves strict-overlap accuracy on both corpora and beats a label-derived second map, but it is the least faithful of the three readouts to the classifier's causal map, its advantage depends on the box rule, and, this benchmark releasing no localization validation set, every design choice behind it was made on the boxes it is scored on. Its one clean transfer beats one baseline and loses to the other.
Read the full abstract

Computational Finance

Disentangling Liquidity-Constrained from Strategic Default: A Deep Learning Approach

Arka P. Bandyopadhyay

I use a deep neural network (DNN) on a proprietary panel of commercial mortgages spanning 1998–2021 to separate liquidity-constrained default from strategic default – two competing, observationally similar explanations for delinquency that are difficult to disentangle with standard parametric models. Conditional on delinquency, property income (net operating income, or NOI) is a more important determinant of the default rate than leverage (loan-to-value, or LTV), despite LTV's status as the workhorse variable in the commercial mortgage default literature. I recover borrower motive from otherwise observationally equivalent delinquency states through a joint analysis of default rates across NOI and LTV buckets, and show that the resulting thresholds are stable across the 2008 financial crisis and the 2020–2021 COVID-19 shock to commercial real estate. Because commercial borrowers are firms rather than households, and because responsibility for a missed payment is diffused across an organization rather than borne by a single decision-maker, the moral and reputational frictions that discourage strategic default in the residential setting are attenuated – making commercial mortgages a setting in which strategic behavior should be comparatively easier to detect, and comparatively costly to ignore for investors, servicers, and regulators.
Read the full abstract

Hardware Architecture

Memory Bandwidth, Not FLOPs: Profiling and Accelerating Query-Based Segmentation Decoders on Edge GPUs

Oliver Busemann, Torben Töniges and Martin Atzmueller

Query-based segmentation models achieve strong performance even under real-time inference on workstation GPUs. On edge devices, however, we show their transformer decoders are deeply memory-bandwidth-bound, a bottleneck invisible to standard FLOP analysis that worsens with input resolution and limited DRAM bandwidth. An FP16 roofline analysis with tensor-core GEMMs active and hardware DRAM counters shows that the non-tensor-core aggregates of FastInst and Mask2Former reach only $2.5\%$ to $6\%$ of the CUDA-core ridge yet account for $53\%$ to $70\%$ of decoder time and $61\%$ to $71\%$ of decoder bytes. The largest individual kernels sustain up to $90\%$ of nominal peak DRAM bandwidth, effectively saturating the memory bus. The bottleneck is therefore not primarily low GEMM intensity, but cross-kernel activation traffic. CompactInst addresses this bottleneck using parameter-free spatial pooling at $4{\times}$, which reduces the bytes moved within the transformer decoder, while a two-convolution refinement head recovers spatial detail. Under TensorRT FP16 on Jetson Orin Nano, CompactInst delivers decoder speedups from $2.35{\times}$ to $4.74{\times}$ and model speedups from $1.57{\times}$ to $2.62{\times}$ as input resolution grows, while closely matching accuracy ($-0.4$ AP on COCO val2017, $+0.2$ AP on Cityscapes test). A heavier variant with $2.57{\times}$ more decoder FLOPs still runs its decoder $1.74{\times}$ faster on the most bandwidth-constrained device, confirming at the deployment level that decoder bytes, not FLOPs, govern latency.
Read the full abstract

Computation and Language

A Large-Scale Dataset for Multi-Class Financial News Classification in Brazilian Portuguese

Leomax Bandeira, Gabriel Aguiar, Dalton Cézane Gomes Valadares et al. (+4 more)

The development of Financial Natural Language Processing (NLP) systems for Brazilian Portuguese is hindered by the scarcity of domain-specific datasets. To address this, we present a large-scale corpus of approximately 160,000 Brazilian Portuguese financial news articles collected from web sources. To establish initial benchmarks for a weakly supervised multi-class classification approach based on semantic similarity, we annotated subsets of this corpus both manually and using a Large Language Model (LLM). We evaluated three similarity-based methods – cosine similarity, K-Nearest Neighbors (KNN), and FAISS-based nearest-neighbor search – using multilingual semantic embeddings. Our experiments reveal that the task is highly sensitive to label quality and class distribution. On the manually labeled subset, KNN achieved the best performance (47.3% accuracy, 31.9% F1-score), closely followed by FAISS. Conversely, on the LLM-annotated subset, while accuracy reached approximately 50%, F1-scores dropped to near 20%, highlighting the negative impact of label imbalance and noisy weak annotations. These findings establish foundational baselines for a challenging task, underscoring the critical need for high-quality manual annotations. Ultimately, this dataset and our preliminary results provide a reference point for future research in Brazilian Portuguese Financial NLP.
Read the full abstract

All authors Leomax Bandeira, Gabriel Aguiar, Dalton Cézane Gomes Valadares, Luiz Pereira, Helder Fernando de Araújo Oliveira, Gustavo Xavier, Andson M. Balieiro

Computational Physics

BBun: an unsteady vortex-ring panel method for interacting lifting bodies, box wings and propellers

Daniele Peri

This report documents BBun (Blunt Body unsteady), a low-order code for the unsteady potential flow around one or more interacting three-dimensional bodies. The bodies are represented by vortex rings (piecewise-constant doublets) with a Neumann boundary condition; free vortex sheets are shed from the trailing edges and, optionally, from the tips, and convected in time, with an implicit unsteady Kutta condition. The report describes the choices that make the discretization consistent and convergent (a single desingularized kernel per wake line, a bordered factorization of the singular Neumann problem, interior velocity conditions for the nearly singular mode of ring-shaped bodies, the detection of the separation lines from the grid connectivity) and the extensions to several bodies, box wings, symmetric configurations (image method), non-lifting bodies, rigidly rotating bodies (propellers), the unsteady Bernoulli equation, a wake-body collision treatment and a strip-wise integral boundary layer. The verification and validation are reported in full: potential flow around a sphere, sensitivity and grid convergence, the two-dimensional limit, an independent vortex-lattice method, the NACA 0015 wing of McAlister and Takahashi (loads and chordwise pressures), the NACA 0012 profile drag, the biplane of Knight and Noyes, Prandtl's best wing system, Wagner's function and blade-element momentum theory for a propeller. A complete aircraft with counter-rotating tractor propellers illustrates the use of the code.
Read the full abstract

Computation and Language

PRISM: PRIvileged Sibling-guided Multi-Agent Topology Design

Phuong Tuan Dat, Qi Li and Xinchao Wang

Multi-agent systems (MAS) based on large language models (LLMs) have become a powerful way to address complex problems, and their effectiveness depends critically on the collaboration topology that decides which agents participate and how they communicate. Recent work learns to generate this topology from the task query, fitting the generator to corpora of execution-verified graphs. The post-training method for such generators remains a limitation: a corpus lists the graphs that solved a query but never ranks them, leaving continued supervised fine-tuning (SFT) with no per-query preference to exploit. Without such a preference, the generator drifts toward the topologies the corpus contains most often rather than those that suit each query, so a gain on one task can come at a cost on another. We propose PRISM, which recovers per-query signal from the same corpus by learning with privileged information: a teacher reads, through a zero-initialized low-rank branch, a sibling graph that also solved the query and is unavailable at deployment, and the student matches its per-decision targets on trajectories the student samples itself. Across six diverse benchmarks PRISM improves over every topology-design baseline evaluated, and matched-teacher controls support the contribution of privileged query information. Code is available in this link.
Read the full abstract

Materials Science

Latent Heat and Raman Spectrum Change on Phase Transition of Water Including Calcium Chloride

Dongha Kim and Changyoun Lee

This study investigates how Raman O-H stretching signatures may be able to track latent-heat-related energetics during water's phase transitions. Prior work on latent heat and Raman analysis of phase change is reviewed to establish theoretical approach. Building on a framework that links O-H frequency shifts to hydrogen-bond strength, we relate entropy/enthalpy variations to temperature-dependent changes in peak position and integrated intensity. Experiments on pure water and impurity-doped samples, specifically CaCl$_2$, were performed under controlled temperatures, and spectra were deconvoluted and integrated over defined bands. The Raman metrics exhibit reproducible temperature dependence that captures the transition window, while CaCl$_2$ induces systematic shifts and measurable modifications in the apparent latent-heat signature. These results highlight Raman spectroscopy as a quantitative probe of thermodynamic evolution and impurity effects in water and related systems.
Read the full abstract

Machine Learning

Contrastive Covariance Subspaces for Activation Steering

Alexandros Xenos, Manos Plitsis, Niki Foteinopoulou et al. (+2 more)

Activation steering controls large language model behavior by adding a direction to hidden activations during inference. For steering to work well, that direction must be a pure signal for the target concept: any confound entangled with it, such as an incidental topic or writing style, is injected into the residual stream alongside the concept itself and degrades the generated text. We introduce Contrastive Covariance Steering (CCS), a training-free method that eliminates this confound variation. CCS projects steering vectors to a low-dimensional subspace obtained in closed form by solving a contrastive variance objective, which retains the directions along which the target concept varies while suppressing directions shared with the other classes. Across three LLMs and four steering domains, CCS consistently beats all baseline steering methods in all $12$ model-domain settings. The largest relative improvement occurs on AxBench and Emotion where we outperform the next strongest steering baseline by $48$ to $70\%$ and $13$ to $27\%$, respectively. Furthermore, CCS outperforms naive difference-of-means steering by up to $151\%$, showcasing the importance of deconfounding concepts. A toy experiment verifies our motivation on why: planting a topic nuisance into the training data reduces unprojected steering by $46\%$, whereas CCS loses only $12\%$ and recovers most of the gap to an oracle that explicitly deletes the planted direction. A human study with $23$ raters on $296$ generations reproduces the LLM judge's ranking. Our extensive ablation verifies the importance of our method's components and robustness to the number of nuisance classes. Finally, we extend our method to multi-turn conversations, where CCS sustains both concept expression and fluency, matching system prompt performance as other steering methods drift.
Read the full abstract

All authors Alexandros Xenos, Manos Plitsis, Niki Foteinopoulou, Yannis Panagakis, Ioannis Patras

Machine Learning

Beyond a Better Score: Long-Horizon Agentic ML Development and Evaluation Protocol for Physics Time Series

Yue Ma, Lucas Venetoulias, Akbota Assan et al. (+1 more)

Physics time-series data are central to fundamental discoveries involving dark matter, neutrinos, and gravitational waves. Machine learning has shown strong potential to recover weak scientific signals buried in complex noise. Recent LLM-agent systems further automate ML development, but existing approaches are often driven primarily by one or a few numerical scores. In pursuit of a better score, agents may exploit shortcuts, trigger mode collapse, or game the evaluation procedure, producing models that achieve high scores but are scientifically invalid. We introduce SIDERIUS, an LLM agent system designed to move beyond a better score toward scientifically valid, long-horizon ML development. SIDERIUS combines contract-defined composable capabilities for flexible orchestration and human-in-the-loop, a multi-layer scientific evaluation protocol that distinguishes valid models from unhealthy or gaming models, and resource-aware exploration for computationally expensive scientific ML. In our TIDMAD benchmark, SIDERIUS with a GPT-based orchestrator achieves the highest Valid-model proposal rate of 63.8% and the best valid denoising score of 2.744, compared with 1.6% and -0.647, respectively, for the same GPT model using the general-purpose Codex coding agent. We further benchmark SIDERIUS on three additional physics time-series datasets, demonstrating its reuse and performance across different tasks. Together, these results suggest that progress in agentic scientific ML should be measured beyond a better score, by how an agent explores and by whether the models it produces can be trusted as science.
Read the full abstract

All authors Yue Ma, Lucas Venetoulias, Akbota Assan, Aobo Li

Machine Learning

Historical Anchors for Scientific Forecasting on Human-Aware Knowledge Graphs

Siu Tin Wu, Ryan C. Barron, Phoebe Upton Sanderbeck et al. (+3 more)

Predicting which scientific connections will form next can point researchers toward the most promising leads. One successful approach learns representations by sampling paths through publication networks, represented by a hypergraph, that connect scientific entities, concepts, and researchers, approximating how knowledge and expertise move through the literature. Sampled paths are then used to train an embedding model to forecast scientific connections such as a property of a material. Performance, however, depends strongly on how many paths are sampled: too little sampling yields incomplete representations, while further sampling can eventually weaken prediction quality. The best sampling budget is therefore often identifiable only after future discoveries are known. We introduce Query–Anchor Agreement (QAA), a diagnostic requiring no future labels or separately trained model. QAA can be used to select a sampling budget, and refine or re-rank the resulting forecast to improve forecasting scientific connections. QAA compares the candidates a model predicts for a target with those most similar to the target's known historical examples, and identifies when these two views converge. Across thermoelectric-material and COVID-19 drug-repurposing benchmarks, repeated random-seed runs, and three sampling policies, QAA-selected budgets fall on average 1.86 percentage points below hindsight-optimal selection for broad candidate recovery. Further, promoting candidates supported by both views, under a capped fusion that bounds the anchor contribution, improves broad recovery across all six benchmark-policy settings, which define the types of network walks used for sampling.
Read the full abstract

All authors Siu Tin Wu, Ryan C. Barron, Phoebe Upton Sanderbeck, Kim Ø. Rasmussen, George Tompkins, Maksim E. Eren

Machine Learning

OPMD: On-Policy Mechanism Distillation Beyond Output Supervision

Yingdong Shi, Zhihong Li, Changming Li et al. (+3 more)

On-policy distillation (OPD) improves language-model by supervising a student on prefixes sampled from its own policy, but its supervision remains confined to the output space. Consequently, OPD transfers what a teacher predicts without supervising the intermediate computation that produces those predictions. Simply distilling intermediate representations like representation matching is insufficient since teacher and student representations may differ geometrically, and even well-aligned hidden states need not be usable by the student's subsequent computation. We introduce On-Policy Mechanism Distillation (OPMD), which transfers teacher-derived intermediate computation while explicitly accounting for its compatibility with the student. OPMD first constructs a student-compatible teacher that transforms teacher representations into intermediate states usable by the student's downstream computation, then it internalizes these states from on-policy trajectories. OPMD achieves the highest average accuracy among the evaluated distillation baselines in all three teacher–student settings, and generalizes to multi-teacher distillation and cross-family supervised fine-tuning. Further analyses show that mechanism supervision yields more effective reasoning and meaningfully alters the student's intermediate computation and solution strategies, supporting that it transfers information beyond output supervision alone. Together, these results establish mechanism-level supervision as an effective way to move on-policy distillation beyond output supervision, enabling students to learn inner mechanisms they can use and internalize.
Read the full abstract

All authors Yingdong Shi, Zhihong Li, Changming Li, Jingyi Yu, Quan Li, Kan Ren

Machine Learning

CoEvoke: Evoking Multi-Agent Collaboration for Trajectory Collection

Lin Wu, Shu Yao, Yuheng Wang et al. (+11 more)

Training multi-agent collaboration requires trajectories of checking, feedback, and repair, yet task-solving rollouts may end in immediate approval or repeat unsuccessful attempts without useful correction. We introduce CoEvoke, a cross-domain framework that evokes these interactions during trajectory collection. Controlled perturbations create recoverable difficulties, while restricted reference-based guidance directs investigation. The resulting dataset contains 4,567 reconstructable trajectories over 4,130 software-engineering and reasoning tasks, linking public interactions to evidence, decisions, and task-native outcomes. Separate experiments over 2,287 same-task pairs show feedback increases of 47.72-100 percentage points across seven perturbation groups; guidance has smaller, model-dependent effects. With identical training tasks, decision-record counts, and updates, perturbation-enriched judge training improves ACPBench-Hard success from 35.38% to 42.12% (+6.73 points). SWE verifier training gains 7.60-9.40 points over interface-matched untrained references. Workflow and post-training evaluations preserve task-solving topology with unperturbed inputs and no private-reference guidance. These results support designing collection conditions to obtain corrective supervision that improves collaborative decisions with frozen solving agents.
Read the full abstract

All authors Lin Wu, Shu Yao, Yuheng Wang, Jingru Fan, Huatao Li, Yihan Li, Liu Yixuan, Cheng Liu, Jian Chang, Zeyu Zhao, Aohua Zhang, Huiying Zhao, Shuyuan Zhu, Chen Qian

Robotics

LabInstruct: Benchmarking Situated Instructional Video Generation for Lab Procedures

Yuming Fu, Weijia Wu, Jing Chen et al. (+5 more)

Self-driving laboratories (SDLs) aim to automate the full experimental loop, from scientific decision-making to physical execution. Ideally, AI-generated plans could be carried out directly by robotic systems, but reliable automation remains difficult in complex, open-world laboratory environments, where experiments often involve fine-grained manipulation, long-horizon procedures, and substantial variation across tasks and setups. Humans therefore remain an important execution interface between AI-generated plans and physical experiments, creating a need for clear and effective human-facing experimental guidance. Because laboratory procedures are inherently visual, spatial, and dynamic, video is particularly well suited to communicating apparatus configurations, manipulation actions, temporal dependencies, and state changes. Recent advances in video generation now make it possible to synthesize experimental demonstrations directly from an initial workspace image and a natural-language instruction. However, whether such models can reliably communicate real laboratory procedures has not been systematically studied. We introduce LabInstruct, a benchmark for situated instructional video generation in real laboratories. LabInstruct contains 204 tasks across 5 scientific disciplines, with real reference executions and structured annotations of objects, actions, contacts, and state transitions. Evaluating 8 frontier image-to-video models, we find that visually plausible generations frequently remain procedurally incorrect, revealing a substantial gap between visual realism and the reliability required for experimental instruction.
Read the full abstract

All authors Yuming Fu, Weijia Wu, Jing Chen, Jiahao Tang, Feifei Chen, Hongyu Zhu, Xin Jin, Alex Jinpeng Wang

Cryptography and Security

Argos: A Multi-Tenant SaaS Architecture for Distributed Edge Security Orchestration

Agustin Javier Di Bartolo, Mohammadhossein Homaei, Andres Caro et al. (+1 more)

The growing adoption of distributed edge devices for security auditing and operational monitoring exposes limitations in lightweight control mechanisms traditionally used to manage such nodes. While commercial Command-and-Control (C2) platforms offer advanced orchestration features, their licensing constraints, operational complexity, and proprietary nature limit accessibility for small and medium-sized enterprises and research environments. This paper presents Argos, a multi-tenant SaaS C2 architecture designed for transparent, automated, and long-term orchestration of distributed edge devices. The framework implements a structured control plane with role-based access control (RBAC), tenant isolation, persistent task management, and cron-based workflow automation. Unlike operator-driven or stateless execution models, Argos enables scheduled and autonomous coordination of security tasks across heterogeneous environments. To formally substantiate its isolation guarantees, the platform is modeled through a set-theoretic authorization framework, and a tenant non-interference property is proven. The proposed architecture was evaluated across three geographically distributed edge devices, executing 810 automated tasks mapped to MITRE ATT&CK techniques. Results demonstrate a global failure rate of 3.33% (95% Wilson confidence interval: [2.30%, 4.81%]) with no statistically significant difference across ARM and x86 architectures (ḩi} 2 = 1.55, p = 0.21), and stable operation under heterogeneous latency conditions, including intercontinental deployments. To ensure scientific transparency and reproducibility, the evaluation methodology, sanitized datasets, and statistical scripts have been made publicly available in an open-source repository.
Read the full abstract

All authors Agustin Javier Di Bartolo, Mohammadhossein Homaei, Andres Caro, Mar Avila

Robotics

RoboHarness: A Simple Harness Outperforms VLA and World Action Models

Bince Qu, Wei Chen and Bo Zhang

The rise of large language models (LLMs) has opened a path toward generalist embodied AI, raising the question of how LLMs can act in the physical world. One straightforward approach is training the model to generate actions: collect robot-action data and video demonstration, refine LLM architecture with an action head, and train a vision-language-action (VLA) model at scale. However, we argue that coding agents have the potential to realize generalist embodied manipulation. All they need is a simple yet effective robot harness. We present RoboHarness: a robotic harness that gives LLM agents a visual-geometric control panel so that they can directly understand and invoke embodied tasks. With RoboHarness, Qwen3.8-Flash-Next outperforms state-of-the-art VLA models on BEHAVIOR Challenge 2025 tasks. The implementation is open source.
Read the full abstract

Machine Learning

Barycentric Anchored Weight Search for Robust Model Merging

Antoni Buades and Jose-Luis Lisani

We propose Barycentric Anchored Search, a post-hoc weight-space procedure for improving fine-tuned vision models under distribution shift without additional gradient training or increased inference cost. Given a pre-trained initialization and two checkpoints fine-tuned on a source dataset, the method constructs barycentric candidate weights and performs a small derivative-free search along directions connecting each candidate to the pre-trained model. Candidate weights are selected using a small validation subset of one or more out-of-distribution (OOD) datasets; the selected model is then evaluated on the held-out portions of those datasets, on additional OOD benchmarks, and on the ImageNet validation set to quantify the robustness-accuracy trade-off. The method is inspired by simplex-based derivative-free optimization, including Nelder-Mead and Torczon multidirectional search, but is specialized to the geometry of neural network weight merging. Unlike Model Soup, which typically benefits from many fine-tuned checkpoints, and unlike Model Stock, which applies a fixed geometric merge, our approach uses only two fine-tuned checkpoints and iteratively adapts the merge using validation feedback from OOD data. Experiments with CLIP ViT-B/32 show that the proposed search substantially improves performance on held-out OOD data, including ImageNet-A, ImageNet-R, and ImageNet-Sketch, while keeping ImageNet accuracy competitive. The resulting weights also improve transfer to OOD datasets not used during candidate selection, outperforming the original fine-tuned checkpoints, naive model soups, and Model Stock in our evaluations. These results suggest that lightweight optimization in anchored weight space provides a practical alternative to fixed weight-averaging rules, geometric merging, or single-model selection.
Read the full abstract

Machine Learning

DShuttleNet: A Badminton Doubles Dataset for Evaluating Team Coordination

Guan-Yi Jhang, Chiencheng Chiang, Wei-Kai Chen et al. (+6 more)

Most existing sports datasets are individual-centric or ball-centric, focusing on individual player actions while ignoring interactions among teammates. In badminton doubles, tactical success is governed by rapid team formation and coordination, yet standard resources for modeling these player interactions are scarce. To bridge this gap, we present DShuttleNet, a comprehensive dataset for badminton doubles curated from elite BWF World Tour tournaments. Beyond trajectory data, DShuttleNet uniquely incorporates expert-labeled "Loss Reasons," transforming the dataset into a diagnostic tool for causal tactical evaluation. We formally define two geometry-driven representations, Teammate-Relative Angle (TRA) and Vertical Shot Angle (VSA), to characterize coordination and shot aggressiveness. To quantify interpersonal synergy, we introduce novel metrics, Court Coverage Efficacy Index (CCEI) and Threat Load Asymmetry Index (TLAI), which evaluate the often-overlooked non-hitting partner's role and defensive coordination. Experimental results demonstrate that conventional models suffer from underfitting when failing to incorporate these coordination-centric features, highlighting the critical importance and potential impact of releasing DShuttleNet. Dataset is available at: https://doi.org/10.34740/kaggle/dsv/16097938.
Read the full abstract

All authors Guan-Yi Jhang, Chiencheng Chiang, Wei-Kai Chen, Hui-Ching Yu, Hsu-Chao Lai, Hwai-Jung Hsu, Wang Chih-Chuan, Jhy-Cheng Huang, Jiun-Long Huang

Neural and Evolutionary Computing

Bias Robustness of Genetic Multi-Criteria Sorting versus Learned Rankers under Proxy Skew and Label Contamination

Vladyslav Shevchuk, Carlos Uziel Pérez Malla and Philipp Wissgott

Learning-to-rank (LTR) models can align rankings with undesignated signals when those signals appear as features or leak into training labels. We compare label-free genetic multi-criteria sorting (open Pikaia strategy variants), which reranks fixed candidate pools using an explicit criteria vector C, to label-trained LTR (LightGBM, XGBoost, RankSVM) under two controlled protocols on MSLR-WEB10K, Baidu-ULTR, WANDS, and Expedia. In the main proxy-skew study, labels remain clean while a calibrated proxy P is available as a feature: Genetic AI rankings show lower Spearman rank-proxy correlation than the LTR peers (e.g. about 0.15-0.16 vs. 0.59-0.87 on WANDS), with both families evaluated jointly on clean nDCG@10 on a bias-utility frontier. In a supporting label-contamination study, training labels are mixed with contaminant B: because Genetic AI methods do not use labels, their bias and utility curves stay flat, whereas LightGBM and XGBoost increase rank-B correlation as contamination rises (OLS bias_slope about 0.58-0.65 on WANDS/Baidu). The results support genetic sorting as an architectural option for optimizing declared attributes on a fixed pool when undesignated proxies or label contaminants must be refused.
Read the full abstract

Machine Learning

Physics-Informed State Space Models for Day-Ahead Photovoltaic Power Forecasting

Phil Aupke, Muhammad Hassan, Khalid Ali et al. (+3 more)

Accurate day-ahead photovoltaic (PV) power forecasting requires both strong temporal modeling and adherence to physical PV system constraints. Purely data-driven models often ignore the underlying PV conversion process and may produce predictions that are outside the operational range of a PV system. In this paper, we propose a physics-informed state space framework that combines a differentiable PV conversion model with a selective state space backbone (PowerMamba). Our approach follows a physics-residual decomposition. The physics module provides a structured baseline based on solar geometry, irradiance, temperature effects, and inverter limits, while the state space model learns residual corrections from numerical weather prediction (NWP) inputs over a 24-hour horizon. Experiments on one year of utility-scale PV data show that the proposed method significantly improves forecasting accuracy, reducing RMSE by 38.5% and MAE by 45.8% compared to a physics-only baseline, and outperforming a purely data-driven model. Results further show that incorporating system-level physics provides the largest performance gains, while additional refinements offer only marginal improvements. Beyond accuracy, the model improves robustness by constraining predictions toward physical feasibility, reducing unrealistic predictions under corrupted measurements.
Read the full abstract

All authors Phil Aupke, Muhammad Hassan, Khalid Ali, Seema, Andreas Kassler, Andreas Theocharis