Peer Revenue Impact factor: volatile

Papers

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

Computer Science

cs Watch Computer Science

Wednesday 30 September

Game Theory

Efficiency of Generalized Proportional First-Price Auctions Under Auto-bidding

Yang Cai, Vineet Gupta, Yanchen Jiang et al. (+4 more)

Auto-bidding is now widely adopted in online advertising platforms, allowing advertisers to specify high-level campaign objectives–such as maximizing total value subject to a return-on-spend (ROS) constraint–rather than manual per-query bids. A central question in algorithmic mechanism design is characterizing the worst-case efficiency loss, or Price of Anarchy (PoA), across auction formats in this prior-free setting. While randomized auctions are known to strictly improve efficiency over deterministic mechanisms for two bidders, two fundamental questions have remained open: (1) what is the optimal PoA for two bidders, and (2) can any mechanism beat the barrier of 2 for general $n \ge 3$ bidders? We resolve both questions using the family of $r$-proportional first-price auctions ($\text{pFPA}_r$), in which each bidder wins with probability proportional to their bid raised to an exponent $r > 0$ and pays their bid upon winning. First, for two bidders, we prove that the standard proportional first-price auction ($r = 1$) achieves a tight $\text{PoA} \le 1.5$, complemented by a matching lower bound showing that no anonymous, monotone mechanism can do better. Second, for general $n \ge 2$ bidders, setting $r = 2n$ achieves $\text{PoA} \le 2 - \frac{1}{4n+1} = 2 - \Omega(1/n)$ across all undominated bid profiles, breaking the deterministic barrier of 2 for every finite $n$ and asymptotically matching the known $2 - \Theta(1/n)$ lower bound.
Read the full abstract

All authors Yang Cai, Vineet Gupta, Yanchen Jiang, Christopher Liaw, Aranyak Mehta, Grigoris Velegkas, Di Wang

Distributed Computing

Cascadia: A Control-Plane-Free Alternative to Hyperconverged AI Infrastructure

Matias Parij, Pawan Paudel, Tate Berenbaum et al. (+1 more)

We present Cascadia, a system for serving large language models on fleets of commodity Intel AIPCs using their CPU, integrated-GPU, and NPU resources. Every node embeds ingress, scheduling, and execution; inference requests require no dedicated routing control plane. Nodes join a libp2p QUIC mesh using CA-issued ed25519 admission certificates, gossip signed capabilities, exchange live load over direct peer streams, and route OpenAI-compatible requests to eligible peers. An operator-run certificate authority handles admission and fleet management outside the inference path. Three serving modes share one interface: whole-model execution on one node, load-balanced replicas, and pipeline-sharded chains using the compilation and speculative decoding mechanism of our companion paper. Optional KV-cache mobility reuses compatible conversation prefixes after a routing move, with cold recomputation on a miss. Signed response receipts and hash-chained logs support provenance and audit. A three-node Phi-3.5-mini NPU testbed delivered 3.10x the response throughput of its one-node configuration under ten concurrent requests; a separate four-node deployment recorded 4.06x the throughput of direct single-node serving. Paired latency observations, runtime measurements, and internal functional checks characterize the tested configurations. We compare Cascadia with IBM, Nutanix, VMware, and HPE platforms on deployment footprint, hardware requirements, scheduling, scaling, licensing, and trust, using vendor documentation. The paper repository provides benchmark scripts, curated measurements, and a claim-to-evidence map.
Read the full abstract

All authors Matias Parij, Pawan Paudel, Tate Berenbaum, Muthaiah Venkatachalam

Artificial Intelligence · Cross-listed from stat.ME

Always-On Experimentation

Ricardo J. Sandoval, David Arbour, Avi Feller et al. (+1 more)

Generative AI has dramatically accelerated the rate at which new treatments—from novel pharmaceuticals to online marketing campaigns—can be conceived and deployed. As a result, modern experimentation platforms often run continuously, with treatments added as they are ready and removed when they underperform. We formalize this "Always-On" experimental setting, in which treatments can be dynamically generated, added to, and removed from a running experiment, and study the statistical problem of deciding whether to accept or reject each treatment while controlling for the false discovery rate. We develop sequential tests that achieve time-uniform Type-I error control under arbitrary stopping times and "predictable" treatment schedules. Our approach builds on the testing-by-betting framework: we construct test supermartingales for testing the average treatment effect of each treatment, and show that the construction of these test supermartingales is growth-rate optimal in an almost-sure sense.
Read the full abstract

All authors Ricardo J. Sandoval, David Arbour, Avi Feller, Michael I. Jordan

Computer Vision

No Corners Cut: State-Grounded Transitions for Mid-Stream Prompt Switches in Video Generation

Zejing Rao, Ketong Ren, Xiaoqiang Liu et al. (+3 more)

Streaming video generators allow users to dynamically modulate video synthesis via mid-stream prompt switching. Existing streaming methods can respond to the updated instruction while still cutting corners, prematurely realizing goals or taking heuristic shortcuts that bypass necessary intermediate state changes needed for a plausible transition. In this study, we present SEGUE, a novel framework that makes this process explicit and trains the generator to execute these transitions faithfully. At each switch, a training-free planner parses the latest frame and prompts, writes a few segue prompts with roles and durations, and then hands control back to the user's prompt. Furthermore, to address the inherent difficulty of training causal models on short-lived temporal schedules without corrupting preparatory supervision, we introduce SPANDMD, which evaluates each active prompt using the full rollout as temporal context while retaining its DMD residual only within the prompt's assigned span. On OpenTrans-360, a benchmark of 1,800 switches that scores how the old state exits and the new one begins, SEGUE ranks first on all eight transition metrics and raises the overall score over the strongest baseline from 0.866 to 0.887. It also ranks first on four of six instruction-response metrics of StreamAV-Bench, while the planner transfers to frozen autoregressive generators without retraining. Project Page: https://anonymous.4open.science/w/No-Corners-Cut-6C5D/
Read the full abstract

All authors Zejing Rao, Ketong Ren, Xiaoqiang Liu, Yiping Meng, Guoxin Zhang, Fan Tang

Artificial Intelligence

GATE-ST: Gene-Aware Text-image Encoder for Spatial Transcriptomics

Lucas Ni, Jian Luo, Wentao Huang et al. (+1 more)

Spatial transcriptomics enables spatially resolved gene expression analysis from slide-level images while preserving morphological features, providing valuable information for studying disease mechanisms and developing treatments. However, spatial gene expression profiling typically requires expensive and time-consuming tests. While existing image-based prediction optimizations mostly revolve around including positional embeddings and further image-based changes, text-based optimizations remain relatively unexplored. We present GATE-ST, which incorporates text-based inputs into image-based spatial gene expression predictions. With this approach, generated text descriptions of genes are utilized to better spatial transcriptomics prediction results. Gene summaries are put through a text encoder, generating embeddings that integrate with image embeddings through cross-attention layers to align with morphological features. We demonstrate the effectiveness of such text inputs by benchmarking performance against random gene embeddings and multiple other image-text fusion architectures, and show that GATE-ST outperforms these alternatives. Our results demonstrate the effectiveness of GATE-ST in pathology imaging, which may greatly reduce the time and cost of accurate spatial transcriptomic predictions, proving the potential of text-guided spatial gene expression prediction.
Read the full abstract

All authors Lucas Ni, Jian Luo, Wentao Huang, Chao Chen

Computer Vision

EPIC: Epipolar-Consistent 360{\deg} Immersive Stereo Video Generation

Debabrata Mandal, Dongdong Fu, Jonathon Miller et al. (+3 more)

Immersive displays can enable rich and diverse virtual experiences. Manually authoring every possible experience to realize this potential, however, is prohibitively expensive, difficult to scale, and impractical. Generative AI models could remove this bottleneck, but today's models are built for conventional displays and cannot generate the high-resolution, stereoscopic $360^\circ$ content required for immersive viewing. Further, temporal and stereo inconsistencies that may be tolerable on conventional displays can become highly disruptive when viewed through an immersive headset. Here, we address this gap with a zero-shot generative pipeline that extends existing video diffusion models into 4K stereoscopic $360^\circ$ videos. Inspired from binocular vision and depth perception, we develop an epipolar-aware $360^\circ$ image matching metric that captures the temporal and stereo geometric inconsistencies across views. We then use this metric as a preference signal for direct preference optimization with limited training data. Our work enables $360^\circ$ stereo video generation and provides a scalable path for bringing generative content to immersive displays, allowing diverse mixed reality experiences on demand.
Read the full abstract

All authors Debabrata Mandal, Dongdong Fu, Jonathon Miller, William Villareal, Xi Peng, Praneeth Chakravarthula

Data Structures and Algorithms

Faster network motif discovery by counting isomorphic subtrees

Tarek Tohme and Joshua A. Grochow

We develop a new algorithm for counting the number of subgraphs of a network isomorphic to a given query graph (#SubgraphIsomorphism), motivated by network motif search. High-degree vertices (hubs), common in real-world networks, contribute to a combinatorial explosion in the number of subgraphs, making existing motif search algorithms intractable for motif sizes greater than $\approx 8$ on a wide variety of networks of interest. Our procedure leverages the $k$-core decomposition and a novel subtree-counting technique to quickly scan the periphery of a network. These two innovations allow our algorithm to significantly speed up its predecessors in practice, especially as most real-world networks have a relatively large periphery. We prove that #RootedSubtreeIsomorphism, a key subroutine in our algorithm, is #P-complete via a reduction from counting bipartite matchings. We provide analytic upper bounds on our algorithm's execution time, and evaluate its performance on 11 real-world networks of varying topologies.
Read the full abstract

Data Structures and Algorithms

Auction-Based Algorithms for Matroid Intersection: Near-Linear Query Complexity and Constant-Pass Semi-Streaming

Chien-Chung Huang and Yusuke Kobayashi

In this paper, we develop a new auction-based framework for matroid intersection and use it to obtain improved approximation algorithms in several computational settings. Our framework is inspired by Fleiner's generalized stable matching algorithm and extends the semi-streaming auction algorithm for bipartite matching due to Assadi, Liu, and Tarjan. Using this framework, for any $\varepsilon > 0$, we present a simple $(1-\varepsilon)$-approximation algorithm in the rank-oracle model whose query complexity matches that of the current fastest algorithm. Furthermore, by extending this result, we obtain the first $(1-\varepsilon)$-approximation algorithm for the weighted problem that requires only a near-linear number of rank-oracle queries, achieving the best known rank-oracle query complexity for the problem. We also obtain a $(1-\varepsilon)$-approximation semi-streaming algorithm for matroid intersection in the multi-pass streaming model, where the elements of the ground set arrive sequentially. It is the first algorithm achieving this approximation ratio using a constant number of passes and nearly linear space in the ranks of the matroids. When viewed in the standard offline setting, the same algorithm yields the first deterministic $(1-\varepsilon)$-approximation algorithm for matroid intersection that requires only a near-linear number of independence-oracle queries.
Read the full abstract

Artificial Intelligence

Concept-Grounded Attention: A Controlled Evaluation of Graph-Injected Attention, Temporal Versioning, and Epistemic Status

Sachin Dev Duggal, Pradyumna Swarnalatha Ramanna and Alexandros Vassiliades

Knowledge-intensive language-model systems typically represent external knowledge as text chunks or static graphs, with limited support for concept evolution, point-in-time reasoning, and distinctions between validated and inferred knowledge. We introduce the Concept Lifecycle Model (CLM), which represents concepts as persistent, graph-grounded, temporally versioned entities with explicit provenance and epistemic status, and Concept-Grounded Attention (CGA), which injects concept-graph structure into transformer computation through graph-biased self-attention (Form A) and gated cross-attention over concept nodes (Form B). We evaluate the framework in controlled settings using disabled-mechanism baselines. On 200 MuSiQue and HotpotQA questions with retrieval fixed, concept-graph retrieval recovers explicit multi-hop paths but does not improve evidence recall. Form A appears to steer attention, with 2.76 times more attention on gold than distractor concepts, but the same ratio occurs when Form A is disabled; the learned bias is negligible and no answers change. An identity-preserving Form B improves F1 from 0.188 to 0.221, but control concepts yield 0.213, indicating that most of the gain reflects added capacity. On LongMemEval, explicit temporal representation improves answer accuracy by 13 to 25 points across all tested generators, up to 122B parameters, while simplified CLM version resolution performs similarly to dated serialization because concept identity is not established reliably. On a synthetic source-independence task, protocol-derived epistemic status reduces unsupported assertions from 28% to 0.1% in a fine-tuned small model and from 19-68% to 0-5% in 72-122B models. Overall, the results support making temporal validity and epistemic status explicit, while showing that graph-attention diagnostics are not informative without disabled-mechanism controls.
Read the full abstract

Computer Vision

Unveiling the Value of Motion for Cinematic Camera Trajectories

Ziqi Zhou, Yujian Yuan and Laura Sevilla-Lara

Cinematic camera motion is a fundamental storytelling tool, defined not only by where the camera is positioned in the scene, but also by how it moves in terms of direction and speed. Recent work on camera trajectory generation and alignment to text relies on pose-centric representations. While in principle a network could derive direction of movement and speed, we find that in practice this might not happen. In fact, in this paper we discover that decomposing the camera trajectory representation from the traditional per-frame poses to direction and speed has surprising benefits across multiple tasks, including trajectory-to-text alignment as well as text-to-trajectory generation. To accurately evaluate the former, we introduce a simple and reliable protocol that overcomes the limitations of prior evaluation baselines. For the latter, building on this representational insight, we propose a novel generative model for camera trajectories, CineGEN, that achieves superior performance across a variety of metrics. We also propose a novel dataset, CineScript, containing movie clips that are enriched with scene descriptions as well as higher-level metadata. This novel data allows us to test models' ability to capture high-level cinematographic information. We show that, despite its simplicity, representing camera trajectories through direction and speed not only helps numerically to achieve better alignment and generation, but also inherently encodes complex directorial intent.
Read the full abstract

Computer Vision

ReGain: Restoring Subject Fidelity in Personalization on Synthetic Images

Shubhang Bhatnagar, Ishan Bhatnagar, Viraj Shah et al. (+1 more)

Text-to-image diffusion models are personalized to a subject by DreamBooth fine-tuning on a handful of its images. Increasingly, these images come from a diffusion model rather than a camera. We show that fine-tuning on such synthetic images degrades subject fidelity, producing oversaturated color and excess high-frequency detail. To isolate the cause, we fine-tune two models from the same base model with the same DreamBooth recipe, one on real photos of a subject and one on synthetic images of that subject generated by the first. We trace the degradation to classifier-free guidance (CFG). For the model personalized on synthetic images, the angle between the conditional and unconditional noise predictions, and with it the norm of their difference, is much larger than for the model personalized on real photos. This inflation grows toward high frequencies and also appears at other prompts semantically close to the subject, such as its class noun, but not at unrelated ones. We propose ReGain, a training-free correction applied at sampling time that measures how much each frequency band of the guidance is inflated relative to the base model and scales that band down accordingly. ReGain needs no real photos. On Stable Diffusion v1.5, ReGain closes 51-64% of the subject-fidelity gap to the model personalized on real photos, as measured by DINO, DINOv2 and CLIP-I. It also improves subject fidelity on SDXL and SD 3.5 and preserves text alignment on all three backbones.
Read the full abstract

All authors Shubhang Bhatnagar, Ishan Bhatnagar, Viraj Shah, Narendra Ahuja

Computational Complexity

Top-Down Lower Bounds for All Depths

Oliver Korten

We prove that Parity requires $2^{n^{\Omega(1)}}$ size De Morgan circuits of constant depth using a new method which is completely "top-down" in the sense of [HJP95]. The proof relies crucially on the core ideas developed in a line of work [HJP95, PPZ99, MW19, GRSS24] which previously established top-down lower bounds for circuits of depth 3 and 4. We first present a proof of a lower bound $\exp(n^{3^{-d}})$. In this case, nearly all of the relevant combinatorial ideas necessary for the proof are already present in some form in [GRSS24]. We then present two extensions of this argument, the first achieving a lower bound $\exp(\epsilon_d n^{1/(2d-2)})$ for some $\epsilon_d>0$ depending only on $d$, and the second achieving the essentially tight lower bound $\exp(\epsilon_d n^{1/(d-1)})$. These improved results each hinge on establishing a key lemma which quantifies the extent to which a high entropy random variable in $\{0,1\}^n$ will look close to uniform after projecting it onto a random small set of coordinates $R \subseteq [n]$.
Read the full abstract

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

Machine Learning · Cross-listed from stat.ML

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

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

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

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

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

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