46 articles mentioning stable-diffusion-3.5-large
arXiv:2604.20372v1 Announce Type: cross Abstract: We report the first systematic evidence of hallucination in AI models of fluid dynamics, demonstrated in the canonical problem of hydrodynamically unstable transport known as viscous fingering. AI-based modeling of flow with instabilities remains cha
arXiv:2512.05591v2 Announce Type: replace-cross Abstract: Large language model post-training relies on reinforcement learning to improve model capability and alignment quality. However, the off-policy training paradigm introduces distribution shift, which often pushes the policy beyond the trust reg
arXiv:2604.21706v1 Announce Type: new Abstract: We previously introduced a training-free method for dysarthria severity assessment based on d-prime separability of phonological feature subspaces in frozen self-supervised speech representations, validated on 890 speakers across 5 languages with HuBER
arXiv:2602.15861v2 Announce Type: replace-cross Abstract: Text analysis of tabular data relies on two core operations: \emph{summarization} for corpus-level theme extraction and \emph{tagging} for row-level labeling. A critical limitation of employing large language models (LLMs) for these tasks is
arXiv:2604.18518v2 Announce Type: replace-cross Abstract: Uniform Discrete Diffusion Model (UDM) has recently emerged as a promising paradigm for discrete generative modeling; however, its integration with reinforcement learning remains largely unexplored. We observe that naively applying GRPO to UD
arXiv:2604.19147v1 Announce Type: cross Abstract: Scaling Transformers typically necessitates training larger models from scratch, as standard architectures struggle to expand without discarding learned representations. We identify the primary bottleneck in the attention mechanism's linear projectio
arXiv:2601.02993v4 Announce Type: replace Abstract: Retrieval-Augmented Generation (RAG) has become a key paradigm for reducing factual hallucinations in Large Language Models (LLMs), yet little is known about how the order of retrieved documents affects model behavior. We empirically show that unde
arXiv:2601.04052v2 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models have demonstrated impressive capabilities in generalized robotic control; however, they remain notoriously brittle to linguistic perturbations. We identify a critical ``modality collapse'' phenomenon where
arXiv:2604.16862v1 Announce Type: new Abstract: Recent deployments of large language models (LLMs) as autonomous trading agents raise questions about whether financial decision-making competence generalizes beyond specific market patterns and how it should be trained and evaluated in noisy markets l
arXiv:2603.24790v2 Announce Type: replace Abstract: While backpropagation and automatic differentiation have driven deep learning's success, the physical limits of chip manufacturing and rising environmental costs of deep learning motivate alternative learning paradigms such as physical neural netwo
arXiv:2604.05002v2 Announce Type: replace Abstract: Learning from weak, proxy, or relative supervision is common when ground-truth labels are unavailable, but robustness under distribution shift remains poorly understood because the supervision mechanism itself may change across environments. We for
arXiv:2506.08013v2 Announce Type: replace-cross Abstract: Multi-task learning for dense prediction is limited by the need for extensive annotation for every task, though recent works have explored training with partial task labels. Leveraging the generalization power of diffusion models, we extend t
arXiv:2604.16343v1 Announce Type: cross Abstract: Background: LLMs enable patient-facing conversational agents, creating a pathway toward digital twins that capture older adults' lived experiences and behavioral responses across time. A central barrier is personality drift -- inconsistent trait expr
arXiv:2604.17774v1 Announce Type: new Abstract: LLM agents in markets present algorithmic collusion risks. While prior work shows LLM agents reach supracompetitive prices through tacit coordination, existing research focuses on hand-crafted prompts. The emerging paradigm of prompt optimization neces
arXiv:2601.07155v2 Announce Type: replace Abstract: Knowledge distillation (KD) is a widely adopted technique for transferring knowledge from large language models to smaller student models; however, conventional supervised KD often suffers from a distribution mismatch between training and inference
arXiv:2604.15609v1 Announce Type: new Abstract: Test-Time Adaptation (TTA) for black-box models accessible only via APIs remains a largely unexplored challenge. Existing approaches such as post-hoc output refinement offer limited adaptive capacity, while Zeroth-Order Optimization (ZOO) enables input
arXiv:2604.15115v1 Announce Type: new Abstract: Most existing Byzantine-robust federated learning (FL) methods suffer from slow and unstable convergence. Moreover, when handling a substantial proportion of colluded malicious clients, achieving robustness typically entails compromising model utility.
arXiv:2604.13279v1 Announce Type: cross Abstract: Fall detection in elderly care requires not only accurate classification but also reliable explanations that clinicians can trust. However, existing post-hoc explainability methods, when applied frame-by-frame to sequential data, produce temporally u
arXiv:2604.01473v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are powerful tools for answering user queries, yet they remain highly vulnerable to jailbreak attacks. Existing guardrail methods typically rely on internal features or textual responses to detect malicious querie
arXiv:2604.11734v2 Announce Type: replace-cross Abstract: Closed-loop cooperative driving requires planners that generate realistic multimodal multi-agent trajectories while improving safety and traffic efficiency. Existing diffusion planners can model multimodal behaviors from demonstrations, but t
arXiv:2510.20093v2 Announce Type: replace-cross Abstract: Although recent advancements in diffusion models have significantly enriched the quality of generated images, challenges remain in synthesizing pixel-based human-drawn sketches, a representative example of abstract expression. To combat these
arXiv:2604.13806v1 Announce Type: new Abstract: Large Language Models (LLMs) are widely used across many domains, but their scale makes deployment challenging. Post-Training Quantization (PTQ) reduces memory footprint without retraining by leveraging a small calibration set. Recent Hessian-based PTQ
arXiv:2510.04995v3 Announce Type: replace Abstract: Power transforms are popular parametric methods for making data more Gaussian-like, and are widely used as preprocessing steps in statistical analysis and machine learning. However, we find that direct implementations of power transforms suffer fro
arXiv:2604.12946v1 Announce Type: new Abstract: 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 increas
arXiv:2509.22220v2 Announce Type: replace Abstract: Prevalent semantic speech tokenizers, designed to capture linguistic content, are surprisingly fragile. We find they are not robust to meaning-irrelevant acoustic perturbations; even at high Signal-to-Noise Ratios (SNRs) where speech is perfectly i
arXiv:2604.09964v1 Announce Type: new Abstract: We present a family of Kaczmarz-based preference learning algorithms for real-time personalized matchmaking in reciprocal recommender systems. Post-step L2 normalization, common in Kaczmarz-inspired online learners, induces exponential recency bias: th
arXiv:2604.04552v2 Announce Type: replace-cross Abstract: Ensemble methods are widely used to improve predictive performance, but their effectiveness often comes at the cost of increased memory usage and computational complexity. In this paper, we identify a conflict in aggregation strategies that n
arXiv:2604.08964v1 Announce Type: new Abstract: Diffusion Large Language Models (dLLMs) have recently become a promising alternative to autoregressive large language models (ARMs). Semi-autoregressive (Semi-AR) decoding is widely employed in base dLLMs and advanced decoding strategies due to its sup
arXiv:2604.08643v1 Announce Type: new Abstract: User interactions in online recommendation platforms create interdependencies among content creators: feedback on one creator's content influences the system's learning and, in turn, the exposure of other creators' contents. To analyze incentives in su
arXiv:2604.09212v1 Announce Type: new Abstract: Large language models are increasingly deployed in multi-turn settings such as tutoring, support, and counseling, where reliability depends on preserving consistent roles, personas, and goals across long horizons. This requirement becomes critical when
arXiv:2601.18150v2 Announce Type: replace-cross Abstract: Reinforcement learning (RL) for large language models (LLMs) is increasingly bottlenecked by rollout (generation), where long output sequence lengths make attention and KV-cache memory dominate end-to-end step time. FP8 offers an attractive l
arXiv:2604.07853v1 Announce Type: new Abstract: Large language model (LLM) reinforcement learning (RL) pipelines are often bottlenecked by rollout generation, making end-to-end training slow. Recent work mitigates this by running rollouts with quantization to accelerate decoding, which is the most e
arXiv:2604.07888v1 Announce Type: new Abstract: Training LLMs at ultra-low precision remains a formidable challenge. Direct low-bit QAT often suffers from convergence instability and substantial training costs, exacerbated by quantization noise from heavy-tailed outlier channels and error accumulati
arXiv:2604.08037v1 Announce Type: cross Abstract: Talking-head generation has advanced rapidly with diffusion-based generative models, but training usually depends on centralized face-video and speech datasets, raising major privacy concerns. The problem is more acute for personalized talking-head g
arXiv:2604.06475v1 Announce Type: new Abstract: Deep Learning Reduced Order Models (ROMs) are becoming increasingly popular as surrogate models for parametric partial differential equations (PDEs) due to their ability to handle high-dimensional data, approximate highly nonlinear mappings, and utiliz
arXiv:2604.05297v1 Announce Type: new Abstract: Value factorization, a popular paradigm in MARL, faces significant theoretical and algorithmic bottlenecks: its tendency to converge to suboptimal solutions remains poorly understood and unsolved. Theoretically, existing analyses fail to explain this d
arXiv:2604.04195v1 Announce Type: new Abstract: To advance Educational Data Mining (EDM) within strict privacy-protecting regulatory frameworks, researchers must develop methods that enable data-driven analysis while protecting sensitive student information. Synthetic data generation is one such app
arXiv:2604.02355v1 Announce Type: new Abstract: Combining Chain-of-Thought (CoT) with Reinforcement Learning (RL) improves text-to-image (T2I) generation, yet the underlying interaction between CoT's exploration and RL's optimization remains unclear. We present a systematic entropy-based analysis th
arXiv:2411.18235v3 Announce Type: replace Abstract: We study the problem of learning verifiably Lyapunov-stable neural controllers that provably satisfy the Lyapunov asymptotic stability condition within a region-of-attraction (ROA). Unlike previous works that adopted counterexample-guided training
arXiv:2604.04539v1 Announce Type: new Abstract: Reinforcement learning (RL) is a core approach for robot control when expert demonstrations are unavailable. On-policy methods such as Proximal Policy Optimization (PPO) are widely used for their stability, but their reliance on narrowly distributed on
arXiv:2604.04410v1 Announce Type: new Abstract: Aligning language models with human preferences is essential for ensuring their safety and reliability. Although most existing approaches assume specific human preference models such as the Bradley-Terry model, this assumption may fail to accurately ca
arXiv:2604.02532v1 Announce Type: cross Abstract: Post-hoc feature attribution methods are widely deployed in safety-critical vision systems, yet their stability under realistic input perturbations remains poorly characterized. Existing metrics evaluate explanations primarily under additive noise, c
arXiv:2604.02697v1 Announce Type: new Abstract: Quantum Machine Learning (QML) is fundamentally limited by two challenges: barren plateaus (exponentially vanishing gradients) and the fragility of parameterized quantum circuits under noise. Despite extensive empirical studies, a unified theoretical f
arXiv:2601.02031v2 Announce Type: replace-cross Abstract: Pretraining of large language models is not only expensive but also prone to certain training instabilities. A specific instability that often occurs at the end of training is output logit divergence. The most widely used mitigation strategie
arXiv:2604.01337v1 Announce Type: new Abstract: While deep learning has significantly advanced accident anticipation, the robustness of these safety-critical systems against real-world perturbations remains a major challenge. We reveal that state-of-the-art models like CRASH, despite their high perf
arXiv:2604.00277v2 Announce Type: cross Abstract: Energy-based models (EBMs) implement inference as gradient descent on a learned Lyapunov function, yielding interpretable, structure-preserving alternatives to black-box neural ODEs and aligning naturally with physical AI. Yet their use in system ide