374651 results (page 2 of 14987)
-
LogicEval: A Systematic Framework for Evaluating Automated Repair Techniques for Logical Vulnerabilities in Real-World Software
Logical vulnerabilities in software stem from flaws in program logic rather than memory safety, which can lead to critical security failures. Although existing automated program repair techniques primarily focus on repairing memory corruption vulnerabilities, they struggle with logical vulnerabilities because of their limited semantic understanding of the vulnerable code and its expected behavior.…
-
Causal Diffusion Models for Counterfactual Outcome Distributions in Longitudinal Data
Predicting counterfactual outcomes in longitudinal data, where sequential treatment decisions heavily depend on evolving patient states, is critical yet notoriously challenging due to complex time-dependent confounding and inadequate uncertainty quantification in existing methods. We introduce the Causal Diffusion Model (CDM), the first denoising diffusion probabilistic approach explicitly designe…
-
Accelerating Speculative Decoding with Block Diffusion Draft Trees
Speculative decoding accelerates autoregressive language models by using a lightweight drafter to propose multiple future tokens, which the target model then verifies in parallel. DFlash shows that a block diffusion drafter can generate an entire draft block in a single forward pass and achieve state-of-the-art speculative decoding performance, outperforming strong autoregressive drafters such as …
-
ROSE: An Intent-Centered Evaluation Metric for NL2SQL
Execution Accuracy (EX), the widely used metric for evaluating the effectiveness of Natural Language to SQL (NL2SQL) solutions, is becoming increasingly unreliable. It is sensitive to syntactic variation, ignores that questions may admit multiple interpretations, and is easily misled by erroneous ground-truth SQL. To address this, we introduce ROSE, an intent-centered metric that focuses on whethe…
-
Do equation of state parametrizations of dark energy faithfully capture the dynamics of the late universe?
We investigate how strongly late-time inferences about DE dynamics depend on the functional prior used to represent the expansion history. Using identical late-time combinations of CC, DESI BAO measurements, the Pantheon+ SN1a sample, and the H0DN prior, we compare a node-based reconstruction of the reduced Hubble function $E(z)$ with a representative family of smooth low-dimensional DE EoS parame…
-
Parallax: Why AI Agents That Think Must Never Act
Autonomous AI agents are rapidly transitioning from experimental tools to operational infrastructure, with projections that 80% of enterprise applications will embed AI copilots by the end of 2026. As agents gain the ability to execute real-world actions (reading files, running commands, making network requests, modifying databases), a fundamental security gap has emerged. The dominant approach to…
-
GlotOCR Bench: OCR Models Still Struggle Beyond a Handful of Unicode Scripts
Optical character recognition (OCR) has advanced rapidly with the rise of vision-language models, yet evaluation has remained concentrated on a small cluster of high- and mid-resource scripts. We introduce GlotOCR Bench, a comprehensive benchmark evaluating OCR generalization across 100+ Unicode scripts. Our benchmark comprises clean and degraded image variants rendered from real multilingual text…
-
Probabilistic Feature Imputation and Uncertainty-Aware Multimodal Federated Aggregation
Multimodal federated learning enables privacy-preserving collaborative model training across healthcare institutions. However, a fundamental challenge arises from modality heterogeneity: many clinical sites possess only a subset of modalities due to resource constraints or workflow variations. Existing approaches address this through feature imputation networks that synthesize missing modality rep…
-
AbdomenGen: Sequential Volume-Conditioned Diffusion Framework for Abdominal Anatomy Generation
Computational phantoms are widely used in medical imaging research, yet current systems to generate controlled, clinically meaningful anatomical variations remain limited. We present AbdomenGen, a sequential volume-conditioned diffusion framework for controllable abdominal anatomy generation. We introduce the \textbf{Volume Control Scalar (VCS)}, a standardized residual that decouples organ size f…
-
Evolution of Optimization Methods: Algorithms, Scenarios, and Evaluations
Balancing convergence speed, generalization capability, and computational efficiency remains a core challenge in deep learning optimization. First-order gradient descent methods, epitomized by stochastic gradient descent (SGD) and Adam, serve as the cornerstone of modern training pipelines. However, large-scale model training, stringent differential privacy requirements, and distributed learning p…
-
Cycle-Consistent Search: Question Reconstructability as a Proxy Reward for Search Agent Training
Reinforcement Learning (RL) has shown strong potential for optimizing search agents in complex information retrieval tasks. However, existing approaches predominantly rely on gold supervision, such as ground-truth answers, which is difficult to scale. To address this limitation, we propose Cycle-Consistent Search (CCS), a gold-supervision-free framework for training search agents, inspired by cycl…
-
Boosting Visual Instruction Tuning with Self-Supervised Guidance
Multimodal large language models (MLLMs) perform well on many vision-language tasks but often struggle with vision-centric problems that require fine-grained visual reasoning. Recent evidence suggests that this limitation arises not from weak visual representations, but from under-utilization of visual information during instruction tuning, where many tasks can be partially solved using language p…
-
Modeling Co-Pilots for Text-to-Model Translation
There is growing interest in leveraging large language models (LLMs) for text-to-model translation and optimization tasks. This paper aims to advance this line of research by introducing \textsc{Text2Model} and \textsc{Text2Zinc}. \textsc{Text2Model} is a suite of co-pilots based on several LLM strategies with varying complexity, along with an online leaderboard. \textsc{Text2Zinc} is a cross-doma…
-
Distinguishers for Skew and Linearized Reed-Solomon Codes
Generalized Reed-Solomon (GRS) and Gabidulin codes have been proposed for various code-based cryptosystems, though most such schemes without elaborate disguising techniques have been successfully attacked. Both code classes are prominent examples of the isometric families of (generalized) skew and linearized Reed-Solomon ((G)SRS and (G)LRS) codes which are obtained as evaluation codes from skew po…
-
An Optimal Sauer Lemma Over $k$-ary Alphabets
The Sauer-Shelah-Perles Lemma is a cornerstone of combinatorics and learning theory, bounding the size of a binary hypothesis class in terms of its Vapnik-Chervonenkis (VC) dimension. For classes of functions over a $k$-ary alphabet, namely the multiclass setting, the Natarajan dimension has long served as an analogue of VC dimension, yet the corresponding Sauer-type bounds are suboptimal for alph…
-
The Verification Tax: Fundamental Limits of AI Auditing in the Rare-Error Regime
The most cited calibration result in deep learning -- post-temperature-scaling ECE of 0.012 on CIFAR-100 (Guo et al., 2017) -- is below the statistical noise floor. We prove this is not a failure of the experiment but a law: the minimax rate for estimating calibration error with model error rate epsilon is Theta((Lepsilon/m)^{1/3}), and no estimator can beat it. This "verification tax" implies tha…
-
GlintMarkers: Spatial Perception on XR Eyewear using Corneal Reflections
We present GlintMarkers, the first system to perform gaze-driven spatial perception using the inward-facing cameras on XR eyewear. Our key observation is that the cornea acts as a mirror that encodes both gaze direction and visual information about the environment in a small, low-contrast reflection. To extract spatial and semantic information from this reflection despite the camera's limited pixe…
-
Drawing on Memory: Dual-Trace Encoding Improves Cross-Session Recall in LLM Agents
LLM agents with persistent memory store information as flat factual records, providing little context for temporal reasoning, change tracking, or cross-session aggregation. Inspired by the drawing effect [3], we introduce dual-trace memory encoding. In this method, each stored fact is paired with a concrete scene trace, a narrative reconstruction of the moment and context in which the information …
-
Parcae: Scaling Laws For Stable Looped Language Models
Traditional fixed-depth architectures scale quality by increasing training FLOPs, typically through increased parameterization, at the expense of a higher memory footprint, or data. A potential alternative is looped architectures, which instead increase FLOPs by sending activations through a block of layers in a loop. While promising, existing recipes for training looped architectures can be unsta…
-
Adaptive Data Dropout: Towards Self-Regulated Learning in Deep Neural Networks
Deep neural networks are typically trained by uniformly sampling large datasets across epochs, despite evidence that not all samples contribute equally throughout learning. Recent work shows that progressively reducing the amount of training data can improve efficiency and generalization, but existing methods rely on fixed schedules that do not adapt during training. In this work, we propose Adapt…
-
Distorted or Fabricated? A Survey on Hallucination in Video LLMs
Despite significant progress in video-language modeling, hallucinations remain a persistent challenge in Video Large Language Models (Vid-LLMs), referring to outputs that appear plausible yet contradict the content of the input video. This survey presents a comprehensive analysis of hallucinations in Vid-LLMs and introduces a systematic taxonomy that categorizes them into two core types: dynamic d…
-
RMGS-SLAM: Real-time Multi-sensor Gaussian Splatting SLAM
Real-time 3D Gaussian splatting (3DGS)-based Simultaneous Localization and Mapping (SLAM) in large-scale real-world environments remains challenging, as existing methods often struggle to jointly achieve low-latency pose estimation, 3D Gaussian reconstruction in step with incoming sensor streams, and long-term global consistency. In this paper, we present a tightly coupled LiDAR-Inertial-Visual (L…
-
Direct Discrepancy Replay: Distribution-Discrepancy Condensation and Manifold-Consistent Replay for Continual Face Forgery Detection
Continual face forgery detection (CFFD) requires detectors to learn emerging forgery paradigms without forgetting previously seen manipulations. Existing CFFD methods commonly rely on replaying a small amount of past data to mitigate forgetting. Such replay is typically implemented either by storing a few historical samples or by synthesizing pseudo-forgeries from detector-dependent perturbations.…
-
Revisiting the angular size-redshift cosmological test with milliarcsecond radio structures in active galactic nuclei
VLBI measurements of the sizes of compact extragalactic radio sources, jetted active galactic nuclei, provide data for probing the angular size--redshift relation, offering a complementary test to other distance--redshift methods. We analyse a significantly expanded dataset to reassess the angular size--redshift relation and its potential for constraining cosmological model parameters, focusing …
-
Task Alignment: A simple and effective proxy for model merging in computer vision
Efficiently merging several models fine-tuned for different tasks, but stemming from the same pretrained base model, is of great practical interest. Despite extensive prior work, most evaluations of model merging in computer vision are restricted to image classification using CLIP, where different classification datasets define different tasks. In this work, our goal is to make model merging more …