Information Retrieval
Self-Indexing Attention for Compression-Compatible Sparse Long-Context LLM Inference
Xu Yang, Jiapeng Zhang, Yuxin Chen et al. (+4 more)
Sparse long-context inference requires efficient
token retrieval in both prefill and decode. Existing methods often use different
retrieval strategies for the two stages, preventing one
retrieval representation from being reused throughout inference. We propose Self-Indexing
Attention, a training-free framework built on a shared transform-domain sign-magnitude representation. The key signs provide a reusable
token-level index for grouped prefill selection and decode
retrieval, while the same representation remains compatible with external KV-cache compression without separate indexer metadata. This 1-bit index enables efficient
retrieval through bitwise operations widely supported by modern accelerators. At 5%
attention density, Self-Indexing
Attention remains close to dense
attention on LongBench and RULER and achieves up to 6.1x prefill and 10.3x decode
attention-operator speedups. Experiments with TurboQuant and DeepSeekV4-Flash further demonstrate compatibility with low-bit KV-cache compression and pretrained sparse-
attention indexers.
Read the full abstract ▾
All authors Xu Yang, Jiapeng Zhang, Yuxin Chen, Feiqiang Sun, Chengguang Xu, Feng Jin, Zhuo Tang
Computational Engineering
Robust topology optimization with non-Gaussian material fields using polygonal finite elements
Nilton Cuellar, Anderson Pereira, Ivan F. M. Menezes et al. (+1 more)
We present a computational framework for robust
topology optimization that integrates polygonal finite-element discretizations, spatially correlated non-Gaussian material modeling, and non-intrusive
polynomial-chaos surrogates. Spatial uncertainty in Young's modulus is represented as a homogeneous non-Gaussian random field obtained via a memoryless transformation of a truncated Karhunen-Loève expansion, ensuring physical admissibility through positivity of stiffness while preserving the prescribed autocovariance. Polygonal finite elements provide a stable discretization for density-based optimization on unstructured meshes and mitigate checkerboard artefacts and mesh bias, while the sparse
polynomial-chaos expansion enables efficient estimation of low-order statistical moments required by the robust objective at a fraction of the cost of intrusive or Monte Carlo approaches. Numerical studies on a cantilever and a curved beam show that introducing non-Gaussian material variability leads to systematic load-path redistribution and a reallocation of 6-12% of the structural volume, together with a reduction in compliance scatter. The non-intrusive surrogate reproduces intrusive reference results within 3% using an order of magnitude fewer full finite-element analyses. These results demonstrate that the proposed framework offers a physically consistent and computationally efficient route to
topology-optimized designs that remain reliable under realistic material uncertainty.
Read the full abstract ▾
All authors Nilton Cuellar, Anderson Pereira, Ivan F. M. Menezes, Americo Cunha Jr
Artificial Intelligence
How Language Models Choose Sides: Internal Representations of Instruction Hierarchy
Enrique Balp-Straffon, Chih-Hao Hsu, Rushiraj Gadhvi et al. (+3 more)
We study how instruction-tuned LLMs arbitrate direct conflicts between system and user instructions. We introduce a
benchmark of 41 paired constraints with deterministic verifiers and evaluate eight models under matched baseline, conflict, and same-channel control conditions. Behaviourally, the models split into three regimes by System Authority Delta: hierarchy-respecting models use the system channel as an authority signal, anti-hierarchy models follow the system less often than their same-channel baseline predicts, and no-effect models show little channel sensitivity. Llama-3.1-8B is the strongest anti-hierarchy case in our suite, following the system in only 0.10 of conflict trials. We use this behavioural failure case to ask whether user-preferring arbitration reflects the absence of an internal conflictresolution signal. It does not: on Llama-3.1-8B, the conflict outcome is linearly decodable from residual-stream activations at 0.97 balanced accuracy, 17 percentage points above a metadata-only baseline, with analogous signals on Qwen2.5-7B and gpt-oss-20b. Steering with a layer-12 mean of four per-conflict logistic-regression directions raises genuine system compliance from 0.132 to 0.530, while directions selected mainly for pooled separability steer poorly. User-preferring conflict resolution can therefore coexist with a readable internal arbitration signal, and successful intervention depends on the geometry of the readout rather than probe accuracy alone
Read the full abstract ▾
All authors Enrique Balp-Straffon, Chih-Hao Hsu, Rushiraj Gadhvi, Sunishchal Dev, Callum Stuart McDougall, Anusha Mujumdar
Artificial Intelligence
Self-Specialized Teachers for Domain Post-Training
Yifei Li, Rongman Xu, Lingling Zhang et al. (+5 more)
Target-only post-training can improve performance in a specialized domain while degrading behaviors that a general-purpose base model acquired before adaptation. We study this problem when target-domain data are available but a representative replay corpus is not. We propose self-specialized teacher
distillation (SSTD), a two-stage procedure that first trains a copy of the base model into a domain teacher, then distills its
token distribution to a student on prefixes sampled from the student itself. Teacher training combines standard target supervision with base-aware key-
token weighting and distribution
alignment to the frozen base model; on-policy
distillation then places domain feedback on states the student can encounter at inference time. On financial numerical
reasoning, medical question answering, and legal holding identification, SSTD retains much of the target improvement of direct fine-tuning while improving the mean score on the evaluated general suite by 4.8–5.0 points at the reported operating point. The pattern persists across Qwen3 sizes and on Gemma backbones. SSTD requires neither an external teacher nor general replay data.
Read the full abstract ▾
All authors Yifei Li, Rongman Xu, Lingling Zhang, Muye Huang, Zihan Ma, Jiashuai Liu, Hang Yan, Heng Wang
Computer Vision
Few-Shot Cross-Dataset Adaptation for Tuberculosis Detection Using DenseNet
Bidhan Biswas, Shahadat Hossain Sohag, Nabil Ashab et al. (+2 more)
Tuberculosis (TB) is one of the most common and dangerous bacterial ailments. Every year, it causes a large number of deaths worldwide. Although many deep learning models can detect tuberculosis from chest X-rays quite accurately, severe domain shift across
datasets makes the task challenging. Different imaging protocols, patient demographics, and equipment across domains make the task of generalization difficult. In real-world settings, a model may perform well on one
dataset but show a noticeable drop in performance when tested on another. In this work, we address this domain adaptation challenge through a few-shot scaling study. A controlled cross-
dataset evaluation is presented in this paper using TBX11K as the source domain and the Mendeley TB
dataset as the target domain. It is investigated how varying the number of target samples affects model performance under three training regimes: frozen backbone adaptation, full fine-tuning of a source-pretrained DenseNet121 model, and training from scratch. The results indicate that the model can perform well even with limited data and can achieve 98.36% accuracy with just 75 labeled samples per class. The adaptation curves demonstrate how fine-tuning effectively mitigates domain shift. These findings establish full fine-tuning of pretrained models as a highly effective and practical strategy for mitigating domain shift in low-resource clinical deployment scenarios.
Read the full abstract ▾
All authors Bidhan Biswas, Shahadat Hossain Sohag, Nabil Ashab, Soumit Kumar Kundu, Saif Mahmud Parvez
Computer Vision
AI Visual Inspection for Garment Production
Ray Wai Man Kong, Ding Ning and Theodore Ho Tin Kong
The garment manufacturing industry is under increasing pressure to improve product quality, reduce costs, and accelerate digital transformation toward Industry 4.0. One of the most challenging quality-control activities is sewing-line inspection, where defects such as broken stitches and skipped stitches are difficult to detect consistently through manual inspection. Human-based inspection is often affected by fatigue, subjective judgement, and inconsistent performance, resulting in defect leakage, rework, and reduced production efficiency. This study presents the development and validation of an Artificial Intelligence (AI)-based visual inspection system for garment sewing-line quality control. The system utilizes Convolutional Neural Networks (CNNs) to detect sewing defects and was initially trained using black fabric and black sewing thread samples. Experimental testing was conducted on black, red, dark green, light blue, silver, and fluorescent yellow fabrics. The results demonstrated successful detection of jump sewing-line defects on black, red, and dark green materials, while performance limitations were observed for broken sewing-line defects and fabrics with significantly different visual characteristics, including light blue, silver, and fluorescent yellow colours. These findings indicate that model accuracy is strongly influenced by the diversity of training data and the ability to generalize across different fabric and thread colours.
Read the full abstract ▾
Computer Vision
Aligning Human Sense: Calibrated Distributional Reward Learning for Video Generation
Nai-Xin Zhai, Weihua Cheng, Dexu Yu et al. (+9 more)
Video generation is central to AI-powered content creation. Aligning generated
videos with human preferences is a key criterion for evaluating generation quality. Despite significant progress in visual quality, three key challenges remain. First, the reliability of reward signals is constrained by the quality of human preference data, which is often affected by subjective noise and bias. Second, standard scalar reward models collapse multi-aspect human preferences into a single value, leading to the loss of dynamic trade-offs across multiple preference dimensions. Third, in policy optimization, the widely adopted KL divergence imposes primarily local constraints and may fail to capture the global structure of human preferences. To address these challenges, we propose a unified preference-aware learning framework for
video generation. First, we introduce elite-guided filtering to calibrate preference data and construct reliable supervision for reward model training. We then model
video quality as a multidimensional reward distribution to capture the uncertainty inherent in human preferences, and use the Wasserstein distance to align the learned reward distribution with the empirical human preference distribution. Finally, we introduce Wasserstein-based distributional
alignment into GRPO, guiding policy optimization to better match the global structure of human preferences over
videos. Experiments on reward modeling and
video generation demonstrate that our approach improves the reliability of reward signals and the perceptual consistency of generated
videos. Our code is available at https://github.com/alignhs26/ahs.
Read the full abstract ▾
All authors Nai-Xin Zhai, Weihua Cheng, Dexu Yu, Yikai Gu, Hanwen Du, Junchen Fu, Chenxi Huang, Yingwei Song, Liyuan Lillian Ma, Yang Ran, Youhua Li, Yongxin Ni
Computer Vision
EditStream: A Unified Autoregressive Framework for Interactive Video Generation and Editing
Yuqian Zhou, Zhenghong Zhou, Zongze Wu et al. (+5 more)
Interactive
video generation and editing are becoming increasingly important for creative design. In this report, we introduce EditStream: a unified framework for interactive
video generation and editing. EditStream unifies multiple
video creation and manipulation tasks within a single DiT-based model through flexible task-specific conditioning, and further transforms it into a fast, few-step autoregressive model for efficient streaming. It supports Text-to-
Video, Image-to-
Video,
Video-to-
Video, Editing Propagation, Reference-guided
Video Editing, and Camera Pose Change, enabling flexible control over
video generation, transformation, and editing within one system. To make the unified model practical for interactive use, we develop a two-stage
distillation approach that combines Velocity Moment Matching (VMM) with autoregressive unrolling. VMM matches conditional velocity moments at student-reached intermediate states to preserve generation quality and motion, while unrolling exposes the student to its own autoregressive predictions to improve temporal stability. Together, they alleviate common challenges in few-step autoregressive
video generation, including over-saturation, degraded motion, temporal instability, and complex training. EditStream provides a practical and scalable solution that bridges high-quality
diffusion-based
video models with interactive creative workflows.
Read the full abstract ▾
All authors Yuqian Zhou, Zhenghong Zhou, Zongze Wu, Cameron Smith, Richard Zhang, Jiebo Luo, Eli Shechtman, Zhe Lin
Computation and Language
Agentic Security: A Systematization of Tools, Failure Modes, and Design Laws for LLM-Driven Penetration Testing
Israt Moyeen Noumi, Tarannum Ahmed Nowshin, Md. Mehedi Hasan Nipu et al. (+3 more)
Agentic security uses large-
language-model (LLM)
agents to plan, dispatch, and interpret security tools. As these systems move from demonstrations to deployed products, practitioners repeatedly encounter the same operational failures. We systematize these failures through a hands-on evaluation of ten widely used static, dynamic, cloud, orchestration, and AI red-teaming tools for unattended pipelines. We introduce a four-dimensional Integration Friction Index that separates one-time engineering cost from recurring organisational, legal, and maintenance cost. We then derive quantitative regularities that explain recurring failure modes. Modelling an agentic security system as
stochastic LLM policies wrapped by a deterministic mediator, we show that long-lived sessions lose resident evidence with phase count, while short-lived sub-
agents extend the usable horizon according to the compression ratio between raw evidence and its summary. We show that a two-stage verdict cascade multiplies scorer likelihood ratios, but provides little benefit when scorer errors correlate. We show that treating unevaluable outcomes as attack failures biases downstream measurements toward evasive and severe responses. We formulate planner-versus-worker model routing as a knapsack problem and derive a closed-form execution cap for heavy-tailed tools, eta* = alpha v/c. Finally, we show why scope and budget enforcement cannot be delegated to system
prompts:
prompts do not constrain what actually executes. Inspectra, our implemented platform, serves as a worked instantiation, with mechanisms labelled shipped, partial, or planned, including those that did not work.
Read the full abstract ▾
All authors Israt Moyeen Noumi, Tarannum Ahmed Nowshin, Md. Mehedi Hasan Nipu, Mohammad Sakib Mahmood, Md. Jakir Hossain, M. F. Mridha
Numerical Analysis
A fully discrete LBRFD-IPDG method for linear fourth-order parabolic equations
Hongying Huang, Hong Zhang and Yanming Zhang
We propose a fully discrete method for linear fourth-order
parabolic equations with Dirichlet boundary conditions, combining an implicit LBRFD multistep scheme in time with a mixed interior penalty discontinuous Galerkin (IPDG) method in space. The temporal discretization employs equispaced linear barycentric rational interpolants and incorporates a startup procedure. To facilitate the spatial discretization, the original problem is reformulated through an auxiliary variable. For certain parameter pairs $(n,d)$, the LBRFD method is shown to be $A(\alpha)$-stable and to possess a wider stability angle than the corresponding BDF$p$ method of the same order. Stability and a priori error estimates are established via a $G$-energy technique and the discrete Grönwall lemma. The theoretical analysis yields a total $L^2$ error estimate of order $h^{k-1}+\tau^p$, where $p=d$ if $n-d$ is even and $p=d+1$ if $n-d$ is odd. The reduced spatial convergence rate is attributed to boundary contributions on $\partial\Omega$. Despite this theoretical prediction, numerical experiments confirm the stability and demonstrate optimal convergence of order $h^{k+1}+\tau^p$.
Read the full abstract ▾
Machine Learning · Cross-listed from quant-ph
Demons on a Budget: Adaptive Measurement Placement at the Entanglement Phase Transition
Rohan Pandey
Monitored
quantum circuits exhibit a measurement-induced phase transition between volume-law and area-law
entanglement as a function of the measurement rate $p$. Prior work places measurements at random locations and treats the rate as the control parameter. We instead fix the measurement budget and vary the placement process, comparing random placement against hand-designed and learned policies in brickwork random Clifford
circuits at matched budget. First, placement geometry matters more than placement information. A deterministic contiguous sweep cuts the half-cut
entropy by a factor of 3.4 relative to random placement, while equal-coverage unstructured placement and a greedy policy with full state access do far worse. The effect is carried by spatial order alone: measuring the $k$ least recently measured sites gives $4.14 \pm 0.06$ bits with random tie-breaking and $1.29 \pm 0.04$ bits with position-ordered tie-breaking. Second, the sweep eliminates the transition rather than shifting it. Tripartite mutual information crossings recede as $p^* \propto 1/L$, the steady-state
entropy saturates at an $L$-independent ceiling near $0.46/p$, and data for $64 \le L \le 512$ collapse onto the form $S = p^{-1} f(pL)$ predicted by a ballistic regrowth argument. Third, in stabilizer dynamics every outcome is deterministic or a fair coin flip, so the record's Shannon
entropy is exactly countable; the sweep dominates the
entropy-versus-record-cost frontier while paying the same roughly one bit per measurement as random placement. Policies trained by cross-
entropy and proximal policy optimization do not find the sweep: score-based policies parameterize which sites to measure, not the order in which degenerate scores are resolved, and the effect lives in that order. The phase diagram of monitored dynamics is a property of the placement process, not only of the measurement rate.
Read the full abstract ▾
Artificial Intelligence
Adversarial Review: Structured Disagreement for Grounded Agentic Code Review
Eric S. Qiu and Joyce Gill
Early multi-
agent LLM systems often used role-separated teams, yet scaling
agent count yields diminishing returns on repository-level coding tasks. Recent alternatives treat
agents as passive tools (subagents), yet this removes the benefits of
agent interaction entirely. We study whether a subagent paradigm can support a middle ground: minimal agentic cooperation without the overhead of large multi-
agent teams. We introduce
Adversarial Review (AR), a minimal cooperative code-review protocol in which a main coding
agent works with a reviewer and a critic
agent. The reviewer evaluates code, while the critic audits the review through structured disagreement before the main
agent edits. On LiveCodeBench, AR achieves the highest pass rate among tested methods, outperforming a five-
agent baseline while using only three
agents. On SWE-PRBench, naive AR exposes a false-consensus failure mode, where
agents converge on agreement without sufficient evidence, but a single
prompt iteration that adds disagreement explicitly achieves the highest F1 among tested methods. On SWE-bench Verified, AR also shows improvements over the baselines on repository-level coding tasks. Together, AR demonstrates that cooperative code review does not require many
agents or complex communication structures: it requires that disagreement be minimal, structured, and evidence-grounded.
Read the full abstract ▾
Computer Vision · Cross-listed from eess.IV
TractoGraphVLM: A Unified Vision-Language Framework for White Matter Tractography
Gurucharan Marthi Krishna Kumar, Janine Dale Mendola and Amir Shmuel
Vision language models have transformed 2D medical imaging, yet extending them to 3D white matter tractography remains challenging due to the complex
topology of fiber bundles. We introduce TractoGraphVLM, a unified framework for four tasks, bundle classification, text-to-tract
retrieval, anatomical captioning, and visual question answering, built on a shared GPS architecture, training procedure, and read-out design. Fiber bundles are represented as streamline graphs whose nodes encode 3D position and tangent orientation. A General, Powerful, Scalable (GPS) graph
transformer produces bundle
embeddings aligned with a frozen BiomedBERT text encoder via contrastive learning, while a BioGPT decoder with visual prefix
tokens generates captions and answers. A single shared encoder and decoder is trained jointly across all four tasks and evaluated from one checkpoint. Trained on HCP Young Adult subjects, TractoGraphVLM achieves 91.8% bundle classification accuracy, 84.7%
retrieval R@1, BLEU-4=20.1, ROUGE-L=66.8, and 66.4% VQA accuracy on a held-out test set. The same checkpoints transfer zero-shot to HCP Aging subjects, with a modest drop on discriminative tasks and a larger drop on generative tasks, showing robustness to age and acquisition shift.
Language supervision yields richer representations than label-only training, recovering structure like hemisphere and fiber family, carried by captions but never given as a label. Swapping only the visual encoder, graphs preserving fiber orientation outperform volumetric baselines, with GPS giving the best balance. Generative metrics measure consistency with a structured knowledge base rather than independent clinical text; even so, TractoGraphVLM shows that classifying, retrieving, describing, and answering questions about a white matter bundle can be served by one jointly trained model that learns transferable neuroanatomy from
language alone.
Read the full abstract ▾
Artificial Intelligence
RDFdL: Integrating RDF with Differential Dynamic Logic
Yuyang Li, Lukas Kubelka, Julia Butte et al. (+1 more)
Knowledge graphs modeled in RDF are powerful for describing static knowledge, but they cannot capture or reason about the dynamic behavior of physical systems, e.g., systems described by differential equations, which is a critical gap for AI-driven cyber-physical systems. To solve this, we propose RDFdL, a framework that integrates RDF with Differential Dynamic Logic (dL) to represent and reason about both static knowledge and the continuous dynamics of physical systems. For the dynamic part, we syntactically represent differential equations and ranges in the state space in RDF and SHACL and provide semantics using a translation to dL. Linking RDF and dL through their shared foundation in first-order logic achieves a unique integration: verification results for safety and reachability properties in the dynamic logic domain become available as entailment to SPARQL queries over RDF data. We implement the pipeline using Apache Jena for ontology-driven RDF
reasoning and KeYmaera X, the
theorem prover for dL, and sketch its applicability in manufacturing.
Read the full abstract ▾
All authors Yuyang Li, Lukas Kubelka, Julia Butte, Tobias Käfer
Computer Vision · Cross-listed from eess.IV
MagViT: Interpretable Multi-Magnification Transformers with Patient-Level Model Selection for Breast Histopathology
Nabil Ashab, Soumit Kumar Kundu, Saif Mahmud Parvez et al. (+3 more)
Breast cancer is one of the most common types of cancer among women around the world. Rapid detection and early treatment can hinder its progress to more complex stages and can impede its spread to other parts of the body. Histopathological image classification is the most common task in cancer detection due to its robustness in analyzing cellular data. Breast histopathology classification requires handling both multi-scale tissue morphology and clinically relevant generalization beyond the source domain. This paper presents MagViT, an interpretable multi-magnification
transformer framework with scale-gated fusion and patient-level model selection. The model uses four BreakHis magnifications (40X, 100X, 200X, 400X) and extracts per-scale representations with a ViT backbone, and combines them via a learnable gate that masks missing scales. Patient-level five-fold cross-validation with a fixed seed has been run and compared with three architectural branches. The most accurate branch is then selected as the final model due to the strongest patient-level accuracy while retaining the simplest fusion pathway. On BreakHis, our architecture achieves a mean image accuracy of 0.9191, a mean patient accuracy of 0.9643, and a mean macro-F1 of 0.9042. External transfer experiments provide preliminary evidence of cross-
dataset generalization under controlled adaptation settings on BUSI (image accuracy 0.8306, macro-F1 0.7480, patient accuracy 0.8291) and IDC (image accuracy 0.8577, macro-F1 0.8191, patient accuracy 0.8372). Grad-CAM visualization indicates that the model focuses on diagnostically significant and meaningful regions across magnifications. Relative to prior ViT-centered BreakHis work, this study emphasizes patient-level selection and cross-
dataset robustness under a reproducible protocol.
Read the full abstract ▾
All authors Nabil Ashab, Soumit Kumar Kundu, Saif Mahmud Parvez, Shahadat Hossain Sohag, Bidhan Biswas, Nazmus Subha
Computer Vision · Cross-listed from eess.IV
ORViT-DR: Ordinally-Robust Hybrid ViT for Low-Resolution Diabetic Retinopathy Grading
Soumit Kumar Kundu, Nabil Ashab, Bidhan Biswas et al. (+4 more)
Diabetic retinopathy (DR) is one of the main causes of impaired
vision. A good and reliable automated grading system can make the screening process safer and more accurate. Because DR stages progress gradually, the task of grading disease severity naturally follows an ordinal structure in which neighboring classes share similar visual characteristics. In this study, ORViT-DR, a hybrid deep learning framework, is designed to improve DR grading from low-resolution retinal images. The proposed approach combines convolutional feature extraction with
transformer-based global context modeling through a pre-trained ViT-Hybrid backbone, which integrates BiT-ResNetv2 with a
Vision Transformer architecture. The approach is tested on the RetinaMNIST subset of the MedMNISTv2
dataset, which contains 28x28 retinal fundus images annotated with five levels of disease severity. To promote stable training and better feature learning, the training strategy applies progressive layer unfreezing, layer-wise learning rate decay, exponential moving average (EMA) parameter updates, and ensemble-based prediction during inference. Experimental results on the official RetinaMNIST test set show that the proposed method achieves 57.00% classification accuracy, along with a quadratic weighted kappa score of 0.5963 and a macro-F1 score of 0.4293. These results suggest that hybrid CNN-
Transformer architectures can provide effective representations for ordinal retinal image analysis.
Read the full abstract ▾
All authors Soumit Kumar Kundu, Nabil Ashab, Bidhan Biswas, Shahadat Hossain Sohag, Saif Mahmud Parvez, Souvik Kumar Kundu, Zunayed Ahmed Rafi
Artificial Intelligence
The Price of Thinking: Reasoning Effort as a Model-Specific API Contract
Yeabin Moon
API buyers purchase a dated contract, not a model name alone: the contract includes the requested and served model,
reasoning-effort term or its omission, output rail, service product,
prompt, and price schedule. We study the
reasoning-effort term through a registered paired contrast of Sonnet 5 with explicit high effort against the same model with effort omitted, using 30 AIME 2026 items and five calls per item. Every paid attempt was assigned one frozen terminal category, and inference resampled items while retaining their repeated calls. Mean delivered cost was \$0.01031 per call higher under the explicit-high contract than under the omitted contract [+\$0.00204, +\$0.01974]. The corresponding accuracy contrast was +0.0133 [-0.0267, +0.0467]; we did not detect an accuracy difference, and the interval permits a gain of up to 4.67 percentage points that this design cannot rule out. Cost per correct answer was \$0.08665 under the high-effort contract and \$0.07662 under the omitted contract, as registered point estimates. A dated contract census, Models-API metadata, and preregistered raw-response probes further documented model-specific omission semantics, including within a provider; claims remained at documentation grade when raw structure was indeterminate. The request registry, parser, terminal taxonomy, statistical plan, and analysis pipeline were frozen before outcomes were examined; the resulting claims are bounded to the model, task, and collection date studied.
Read the full abstract ▾
Multiagent Systems
WONDER: A Radio World Model-based Negotiation Framework for Multi-Agent UAV Coverage Optimization
Jiahao Huang, Rongpeng Li, Zhifeng Zhao et al. (+2 more)
Post-disaster damage to terrestrial infrastructure can disrupt wireless coverage,while Uncrewed Aerial Vehicle (
UAV) swarms provide a promising solution for rapid restoration.However, due to the limitations in local geometry observations hidden
radio impact,and inter-
UAV communication,there exists a significant gap between locally visible movement choices and swarm-level coverage outcomes.To combat this gap,we propose a raido World-model-based Optimized Negotiation framework for Distributed
UAV covERage (WONDER).Particularly, to tackle the unavailability of the future
radio field from onboard observations, WONDER uses a Joint-
Embedding Predictive Architecture (JEPA)-based
radio world model to learn and predict the incremental
radio effect of each candidate trajectory from deployment-available information.Multi-round negotiation in WONDER then coordinates ranked proposals by committing one trajectory at a time and re-evaluating the remaining proposals under the updated context. Our theoretical analyses further validate the effectiveness of such a world model-based framework. WONDER also adopts a Proximal Policy Optimization (PPO)-style Actor and alternates between updating the world model and the actor. Furthermore,we build RadioDynamics,a comprehensive simulation environment that integrates
UAV mobility,
radio propagation, inter-
UAV communication modeling,and digital-twin geometry with ray-traced fields in $62$ metropolitan scenes.Experiments on $11$ testing scenes in RadioDynamics show that WONDER achieves the highest balanced score among seven evaluated methods,reaching $0.870$ with a $0.162$ coverage advantage over STACCA, while maintaining $100\%$ connectivity between
UAVs.
Read the full abstract ▾
All authors Jiahao Huang, Rongpeng Li, Zhifeng Zhao, Guoru Ding, Honggang Zhang
Hardware Architecture
DTX: A Throughput-First Training Accelerator for Diffusion and Transformer Models
Shashank
DTX is a throughput-first training accelerator for
diffusion and
transformer models. Any summation serialized through a single FP32 adder is a loop-carried dependence that pins a machine near 2 FLOP/cycle regardless of physical design; DTX is built so no such chain exists anywhere – every reduction is a pipelined binary tree, every FP operator a two-stage pipeline with initiation interval 1. An 8x8 weight-stationary systolic array with a fused bias/activation/cast epilogue, an 8-lane vector unit, an 8-lane fused AdamW pipeline, and a pipelined Philox Gaussian source are co-issued by a 4-slot VLIW word over a unified 64 KB tile space: 216 FLOP/cycle, roughly 108x the loop-carried floor per clock. With no canonical sum order, verification is tolerance-based against an FP64 golden model, with exact-equality carve-outs and a demonstrably tight bound (a premise-violating program measured 5,340x over budget; 17/17 tests, 107,108 elements, zero failures). Semantic gates confirm an on-device
diffusion-MLP run reduces its loss (56.4 to 26.0), counter-level proof shows compute/DMA overlap sustains the peak, an analytical iso-node decomposition bounds the GPU comparison at 6-10x throughput per watt, and a sky130 campaign hardens the systolic array to DRC-clean GDS at 83.3 MHz post-route – 1.9x an optimized loop-carried MAC baseline on the same node and flow.
Read the full abstract ▾
Multiagent Systems · Cross-listed from q-bio.QM
The Little Scientist: What Does the Scientific Method Buy an LLM Agent?
Travis Smith
Scientific discovery emerges from cycles of hypothesis, implementation, empirical testing, and feedback. Can this process be automated? We approach automated
algorithm design through the lens of the scientific method, where an LLM-based
agent goes through each step of the process in an iterative fashion. Results: We present The Little Scientist, a framework that maps the scientific method onto an LLM
agent in a loop: a Scientist
agent iterates hypothesis, prediction, code, test, and reconciliation inside an evaluation environment that returns structured diagnostics, and a Kuhn
agent injects paradigm-shifting reframings at plateaus. On DNA motif discovery, the process wrote an
algorithm from scratch (DALE) that outperforms STREME across 132 ENCODE transcription factors on the shuffled-negative
benchmark (mean AUROC 0.842 vs. 0.803) while running 11x faster. We then asked why this method worked, and that question became the paper's scientific core: a preregistered, controlled teardown of the framework's own scaffolding consisting of ten ablation arms against one-shot bandit nulls. The answer overturned the premise. Seven of ten loop arms fail to beat a bandit drawing samples from the same model and
prompt, the full scaffold performs below blind sampling at 7-8x the
token cost, and a floor-
prompt arm with no framework at all wins on both score and value per
token. On a held-out genomic
benchmark, the best loop artifact and the best bandit draw agree to within 0.002, and the DALE
algorithm from the initial experiment scored similarly. The convergent picture is that LLM
agents do not reason their way past what training placed in the weights. Autoresearch, on this evidence, is sampling, selection, and remixing, which is the bet the Evolve-family architectures made when they chose populations and external selection over scratchpad
reasoning, and why those choices were right.
Read the full abstract ▾
Computer Vision
CM-MAE: A Physics-Guided Cross-Modal Self-Supervised Learning Framework for Vision-Wireless Applications
Yubo Zhang and Yiyao Liu
Synchronized camera and wireless measurements observe the same scene through different physical channels. The central difficulty is that a representation learned in one deployment can fail when viewpoint, traffic, illumination, and propagation geometry change. This paper presents CM-MAE, a self-supervised
vision–wireless pretraining framework for cross-scenario representation transfer. The evaluated real-data model uses only RGB frames and the measured 64-beam received-power vector available in DeepSense 6G; it does not use ray-traced paths, calibrated depth, or beam-index labels during pretraining. Its central pretraining term is a soft contrastive
alignment loss. Instead of making the synchronized image–wireless pair the only positive pair, this loss builds a target distribution from similarities between measured beam-power profiles, so nonidentical samples with similar directional responses are not forced apart as false negatives. A masked joint decoder provides the complementary local objective by reconstructing hidden visual patches and wireless angular clusters under modality dropout. After pretraining, a differential-rate fine-tuning rule lets a new fusion head adapt quickly while the encoders move slowly. Under a sequence-disjoint DeepSense 6G protocol, adding the soft
alignment loss improves a matched linear-probe transfer average from 24.88% to 29.49%. Mild fusion fine-tuning reaches 77.38% Top-1 accuracy on unseen Scenarios 6–8, and optional transductive normalization adaptation reaches 78.69%. Since the fusion setting uses the contemporaneous 64-beam power vector at inference, these results should be read as representation-transfer diagnostics, not as proactive beam-prediction or reduced-sweeping claims.
Read the full abstract ▾
Machine Learning
The Limits of Binding in Dual Encoders
Kin Ian Lo
Dual-encoder models such as CLIP score an image-caption pair by a single inner product of two independently computed unit vectors, and fail at binding, often scoring near chance when asked to distinguish "a red car and a blue dog" from "a blue car and a red dog". We give a mathematical account of when this failure is necessary and when it is contingent. Working within the ideal-encoder framework proposed by Kang et al., we first show the relevant axioms are satisfiable, so every impossibility must enter through an added, checkable hypothesis. We then prove three such obstructions. Depth: for recursive role-binding codes the swap margin obeys an exact law $m(D) = 2b^{-D}$ in the nesting depth D, with a finite-dimension version holding up to one explicitly flagged concentration estimate; the resolvable depth grows only logarithmically in the dimension and is single-digit at CLIP scale, the nesting depth of ordinary
language. Objective: architecture-free throttle
theorems showing that the contrastive objective's entire reward for binding is bounded by the rate at which training contrasts a caption against its own swap, a rate that vanishes at web scale, and that exactly reversed binding costs only that rate times the mean binding margin; both are verified in simulation. Geometry: a tight smoothness-binding frontier: the closer the two swap-related captions must embed to a shared paraphrase anchor, the smaller the binding margin can be, with an exact constant. Measuring its text-only diagnostic across 18 deployed text encoders, every model sits at roughly 25-35% of its ceiling, and the induced per-item ceiling tracks SugarCrepe's subset difficulty at r = 0.99. Binding failure in deployed dual encoders is thus not a dimension or smoothness limit today, but an incentive and code-structure limit, with a proved depth ceiling that remains once those are fixed.
Read the full abstract ▾
Computer Vision
BagShift: Measuring How Patch Selection Changes the Evidence Seen by Whole-Slide MIL
Ruicheng Yuan, Zhenxuan Zhang, Liwei Hu et al. (+4 more)
Whole-slide multiple-instance learning (MIL) observes only the patches admitted by its selector. Deployment can alter this selector through compute limits, tissue masking, or regional workflows, even when the patch count is unchanged. We introduce BagShift, a paired protocol that changes the selector for the same case while holding its features and predictor fixed, thereby isolating selector response from case mix. With equal 128-patch budgets, sampling across the tissue or concentrating around one coordinate exposes markedly different evidence: on PANDA, the two views reduce quadratic weighted kappa by 1.57 and 17.96 points, respectively (QWK reported on the $\times100$ scale). On CAMELYON16, lesion annotations withheld from model development show that localized views retain tumor in only 10.0% of micrometastatic observations, and matched exposure does not consistently recover the loss. The same fixed-count stressor produces a much smaller response on external lung subtyping, although differences in relative coverage make cross-task severity descriptive. When repeated localized observations are available, unioning their patches before one nonlinear MIL pass improves PANDA QWK by 7.87 points over averaging regional predictions. Patch count specifies computation, not observed evidence; deployment evaluations should report both what a selector preserves and how repeated observations are aggregated.
Read the full abstract ▾
All authors Ruicheng Yuan, Zhenxuan Zhang, Liwei Hu, Anbang Wang, Haijie Xu, Jiawei Luo, Guang Yang
Robotics
Vision-Guided Reorientation and Color Sorting of Writing Utensils Using a Low-Cost 4-DoF Arm
Anirudh Rangarajan and Bibit Bianchini
Low-cost four-degree-of-freedom (DoF) arms are among the most accessible robotic platforms. But they are one joint short for picking up in situations where objects are at arbitrary orientations, a task that appears to require five degrees of freedom: the planar position (x and y), the height (z), a wrist rotation to align the gripper with the object, and gripper actuation, of which a four-DoF arm lacks the wrist rotation. This work uses perception and motion planning so that such an arm, a roughly $200 Waveshare RoArm-M2-S under a fixed overhead camera, can detect and color-sort writing utensils without that joint. A YOLO11n-OBB (You Only Look Once, oriented bounding box) detector locates each writing utensil; camera intrinsics and an ArUco reference pose convert its pixel coordinates to
robot coordinates; and a color classifier labels it. The detected orientation angle determines the motion strategy: utensils close to the arm's fixed approach direction are picked up directly, and those at steeper angles are reoriented via corrective sweeps until they are graspable, after which they are picked up and sorted into the assigned color bin. In 196 single-utensil trials, the 98 that started beyond 45 degrees from that direction all became graspable within four sweeps (130 total). Overall, 176 (89.8%) ended in the correct bin; 19 of 20 failures were slipped or missed grasps, one a mislabeled color. For the seven utensils tested in this setup, corrective sweeps brought every steeply misaligned utensil into a graspable orientation on an arm with no wrist joint.
Read the full abstract ▾
Machine Learning
A Banach-Space Theory of Markovian Halpern Iteration for Non-Expansive Maps
Ege C. Kaya, Arda Fazla, M. Berk Sahin et al. (+1 more)
We study
stochastic approximation of fixed points of a non-expansive operator $T$ when the oracle samples originate from a continuing Markovian trajectory. A direct block-minibatch implementation of Halpern iteration attains an expected last-iterate residual of order $O(\log N/N)$, but accrues a substantive complexity of $\tilde O(\epsilon^{-5})$ Markovian samples. We therefore introduce a variance-reduced Markovian PAGE-Halpern method whose refresh and same-state difference blocks are analyzed through the Poisson equation. In
Hilbert spaces, the cocoercivity of $I-T$ results in an $O(\epsilon^{-3})$ sample complexity. Our main result extends this construction to a general finite-dimensional
Banach space. A displacement-level Halpern bound replaces the
Hilbert-space potential and yields $\tilde O(\epsilon^{-3})$ sample complexity. We also establish a high-probability guarantee with the same leading accuracy dependence by measuring the
estimator in an auxiliary smooth norm.
Read the full abstract ▾
All authors Ege C. Kaya, Arda Fazla, M. Berk Sahin, Abolfazl Hashemi
Machine Learning
Beat the Counter First: A Baseline for Temporal-Graph Anomaly Detectors
Omair Shafi Ahmed and Zohair Shafi
Progress in streaming, edge-level graph anomaly detection (GAD) has been marked by increasingly elaborate architectures, from count-min-sketch chi square tests to
memory-augmented
attention networks. Yet the empirical gains attributable to this added complexity have not been systematically evaluated. We propose SimpleCount, a reference with no parameter fitting that selects one scalar feature per
dataset from a fixed pool of counts, recencies, first-occurrence indicators, and count-derived transforms. We compare SimpleCount with two temporal-graph detector models and an IsoForest control fitted to the complete feature vector across five public
datasets and one synthetic
dataset. SimpleCount matches or exceeds SLADE on three of six
datasets and exceeds IsoForest on all six. We report paired statistical tests and five-seed SLADE evaluations. SLADE requires 23 to 133x more wall-clock time than SimpleCount. On Synth-Triangle and an additional Synth-Quad probe, pre-event structural scores recover the planted signal at AUC up to 0.955, while all evaluated detector models remain near random. The benefit of complexity is
dataset-dependent, and every claimed gain should be reported against a strong one-feature reference together with its compute cost.
Read the full abstract ▾
Computation and Language
LLMs Get Smarter from Targeted Synthetic Multilingual Data
Ishika Agarwal, Arkajyoti Charaborty, Tanner Sorensen et al. (+2 more)
Language-specific competency (LSC) is the phenomenon of a
language model performing better or worse depending on the
language of the
prompt. In other words, a
language model outputs different (and potentially incorrect) responses to the same semantic query when prompted in different
languages. Prior work attributes this to an internal misalignment of semantic representation across
languages. Currently, there are two main approaches to address LSC in the literature: (1) routing all queries through English, improving performance, but limiting
language expressivity to English; or (2) training on
language-balanced data, equalizing model performance across
languages, but reducing overall performance. In this work, we take a data centric perspective and introduce HOTFIXR: Hardness Optimized Training data For Improving X-Lingual
Reasoning. It is a data generation framework that uses models to probe and learn a student model's
multilingual weaknesses, and generates data to mitigate them. HOTFIXR can generate
multilingual synthetic training data that can improve
multilingual performance. We evaluate on three in-distribution tasks, three out-of-distribution tasks, and four out-of-distribution
languages. On average, HOTFIXR (1) improves in-distribution performance by 6.2%, (2) reduces catastrophic forgetting (induced by fine-tuning) on OOD tasks by 3.7%, and (3) on OOD
languages by 7.1%. Overall, as many real-world applications requires
multilingual LLMs, our work contributes to the efforts of making LLMs multilingually proficient. We will release code upon acceptance.
Read the full abstract ▾
All authors Ishika Agarwal, Arkajyoti Charaborty, Tanner Sorensen, Neha Gupta, Andreas Stolcke
Computation and Language
SEER: Long-Context Reasoning via Selective Visual-Text Compression
Jiawei Xu, Zhilin Zhai, Jinrui Fang et al. (+6 more)
Long-context
reasoning remains computationally expensive for large
language models due to the quadratic complexity of
attention over text
tokens. Visual-text compression offers a promising alternative by rendering text into images and processing them with
vision-
language models, often reducing
token usage. However, existing approaches apply uniform compression regardless of query relevance, potentially sacrificing precision where detailed extraction is required. We present SEER, a framework that learns to select query-relevant images through visual scanning and retrieve textual content only where needed, combining the efficiency of visual compression with the precision of text-based
reasoning. Through supervised fine-tuning on tool-interaction trajectories, SEER learns adaptive tool invocation for selection and
retrieval. Experiments on long-context
benchmarks show that SEER improves extraction precision through selective text
retrieval while retaining average
prompt-
token savings relative to full-text baselines. On LongBench, SEER achieves 51.11% average accuracy, outperforming the visual-text baseline Glyph-9B by 2.33 points and Qwen3-8B by 3.49 points. Code can be accessed at https://github.com/jiaweixu98/SEER
Read the full abstract ▾
All authors Jiawei Xu, Zhilin Zhai, Jinrui Fang, Ruohan Xu, Mingfei Lu, Yi Zhang, Guanchu Wang, Tianlong Chen, Ying Ding
Artificial Intelligence
Solvable Sokoban Without a Solver via Diffusion
Sina Baghal
Deciding whether a Sokoban puzzle is solvable is PSPACE-complete (Culberson, 1997): solutions can be exponentially long and there is no short certificate to check. Solvability is also a fragile property, since even a single misplaced wall can silently render an entire puzzle unsolvable. In this work, we show that a
transformer-based discrete
diffusion model trained purely on tile completion, with no access to solvers, rewards, or solvability labels, achieves a solvability rate of 77.4%, with 94.5% of the remaining failures rendered solvable by removing a single wall. In other words, a global, search-heavy property follows from a local training objective: trained only to fill in masked
cells, the model inherits solvability it was never trained on. An autoregressive model factorizes as $p(c_k \mid c_1 \dots c_{k-1})$, meaning a fixed order, always conditioned on a prefix. Masked
diffusion does not: it hides a random subset of
cells and learns $p(c_k \mid \text{any subset})$, so at generation time it can reveal
cells in any order, each one conditioned on everything already placed, wherever it sits on the board. A puzzle's difficulty comes from exactly this kind of non-local interaction, a decision in one part of the grid constraining what will work somewhere else entirely. A generator that is not locked into a single fixed order is therefore a better structural match for the problem than one that is. The training pipeline is adapted from MD4 (Shi et al., 2024) and the
dataset is DeepMind's Boxoban (Guez et al., 2019). The trained model and instructions for generating puzzles are publicly available.
Read the full abstract ▾
Artificial Intelligence
Navigation-Informed Embeddings: Dense-Retriever Adaptation from Agent Search Traces
Shrey Shah and Levent Ozgur
Agentic
retrieval workflows produce query,
retrieval, and stopping traces as a byproduct of answering questions. We study how these traces can adapt a deployed dense retriever to changing workflow distributions without new relevance labels, synthetic queries, or LLM judgments. We introduce
Navigation-Informed
Embeddings (NIE), a family of trace-derived objectives. NIE-Stop turns the stopping document into a soft positive; NIE-Path additionally uses preceding path documents as hard comparisons and imposes ordinal constraints with
geometric decay. A BGE encoder adapted from retained source trajectories improves support Recall@20 on an independent target
benchmark from 72.2 to 78.0 overall. NIE-Stop reaches 76.9 overall and 52.3 on long paths; NIE-Path raises long-path performance to 55.4, compared with 46.7 for the unadapted encoder. A shuffled-order control under the full path objective loses 3.2 points. Without public-
benchmark training, the same adapter also improves nDCG@10 by 1.9 points on standard BEIR HotpotQA. NIE therefore provides a lightweight adaptation channel for settings where trajectories are already retained, with zero incremental labeling cost.
Read the full abstract ▾