45 articles mentioning stable-diffusion-3-medium
arXiv:2609.03389v1 Announce Type: cross Abstract: Smectic liquid crystals are layered liquid-crystalline phases characterized by orientational order and periodic density modulation. Although their structures can be modeled using continuum theories, computing stable configurations remains challenging
arXiv:2609.04198v1 Announce Type: new Abstract: Language-model judges now gate training data, score generations, and drive leaderboards. The judge is then a measurement instrument, resting on one rarely stated assumption: the same request, sent to the same model name, reads the same tomorrow. We aud
arXiv:2602.01734v2 Announce Type: replace Abstract: Training instability remains a critical challenge in large language model (LLM) pretraining, often manifesting as sudden gradient explosions that waste significant computational resources. We study training failures in a 5M-parameter NanoGPT model
arXiv:2608.25390v2 Announce Type: replace-cross Abstract: Refusal training protects AI models from jailbreaks by training models to decline unsafe queries, reducing the risk of misuse. Recent work finds that refusal behavior in aligned language models can be mediated by a single activation direction
arXiv:2609.02846v1 Announce Type: new Abstract: Stable 4-bit floating-point (FP4) pretraining is difficult because the E2M1 payload represents only a narrow range of magnitudes. NVIDIA's Transformer Engine \nv{} recipe addresses this with current-tensor scaling, a randomized Hadamard transform (RHT)
arXiv:2609.02354v1 Announce Type: cross Abstract: While traditional stable matching algorithms, such as the Gale-Shapley algorithm, prioritize stability, they may fall short of achieving equitable outcomes among participants. We study the role of \emph{Nash social welfare} (NSW) as a fairness object
arXiv:2609.00621v1 Announce Type: new Abstract: Prompt optimization can improve multi-agent LLM systems, but the prompts being optimized often serve two entangled roles: generating task-relevant content and specifying execution-critical protocols, such as message routing, output formatting, and term
arXiv:2609.00356v1 Announce Type: new Abstract: Quantum federated learning (QFL) enables clients to train quantum neural network (QNN) models without sharing private data. We find that aggregation in QFL is unstable under heterogeneous data, unreliable communication, variable fidelity, latency, and
arXiv:2608.09870v2 Announce Type: replace-cross Abstract: Uniform stability is a classical tool for controlling the generalization error of a learning algorithm. Bousquet, Klochkov, and Zhivotovskiy (2020) showed that the problem can be reduced to a moment inequality for a sum of weakly interacting
arXiv:2602.01695v2 Announce Type: replace Abstract: Latent reasoning reduces the token-generation cost of chain-of-thought reasoning by replacing explicit intermediate tokens with continuous latent transitions. However, existing latent reasoning methods usually rely on dense and entangled transition
arXiv:2511.11743v4 Announce Type: replace-cross Abstract: Deploying deep neural networks on resource-constrained devices faces two critical challenges: maintaining accuracy under aggressive quantization while ensuring predictable inference latency. We present a curiosity-driven quantized Mixture-of-
arXiv:2605.28802v2 Announce Type: replace Abstract: Free-text explanations extend human label variation (HLV) beyond label disagreement by revealing the reasoning and preferences behind annotators' decisions. We study whether large language models (LLMs) can learn and reproduce such annotator-specif
arXiv:2608.24044v3 Announce Type: replace Abstract: Latent world models plan by predicting how candidate actions advance learned latent dynamics. In self-predictive models, however, the encoder and predictor are optimized jointly and can co-adapt to latent transitions that are easy to predict but we
arXiv:2608.27286v1 Announce Type: new Abstract: Inferring molecular structures from multimodal spectroscopic measurements requires integrating complementary yet highly heterogeneous signals. However, the common paradigm of directly concatenating multispectral sequences can exhibit anomalous performa
arXiv:2608.26602v1 Announce Type: cross Abstract: Large software repositories are often beyond model context limits. Training repository knowledge into models is costly and quickly stale, while local retrieval can miss scattered requirements, and explicit relation graphs add ongoing maintenance burd
arXiv:2603.21491v2 Announce Type: replace Abstract: Stable training is often treated as evidence that learning is succeeding, but stability characterizes optimization behavior rather than correctness relative to an external objective. We study what happens when the signal being optimized remains per
arXiv:2608.22354v2 Announce Type: replace-cross Abstract: Delta-Rule recurrent models maintain a fixed-size state, enabling $O(1)$ inference memory but potentially becoming unstable under extreme-context extrapolation. By tracking RWKV-7 over sequences of up to 100M tokens, we empirically identify a
arXiv:2601.06472v2 Announce Type: replace Abstract: Learning solution operators for differential equations with neural networks has shown great potential in scientific computing, but ensuring their stability under input perturbations remains a critical challenge. We introduce the StablePDENet, a phy
arXiv:2608.24470v1 Announce Type: new Abstract: Heterogeneous agile Earth observation satellite (AEOS) scheduling requires task selection, satellite assignment, and observation sequencing under satellite-dependent visibility windows, attitude maneuvering requirements, energy consumption, and onboard
arXiv:2607.29209v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) broadcasts a single response-level reward to every token, while on-policy distillation (OPD) scores each token against a stronger teacher for a dense advantage but caps performance at teacher qual
arXiv:2607.29363v1 Announce Type: cross Abstract: Balancing sequence length, representational capacity, and long-horizon stability is a central problem in autoregressive (AR) speech and audio generation. Representations with higher frame rates or greater capacity can preserve more signal detail, but
arXiv:2607.27132v1 Announce Type: new Abstract: An agent acting under partial observability must retain a recursively updateable statistic of history that restores the Markov property, but the smallest such statistic is generally unknown. We characterize this minimal Markov sufficient statistic for
arXiv:2607.24953v1 Announce Type: cross Abstract: Reducing training precision is a key lever for improving the e ciency of large language model (LLM) training, but pushing beyond FP8 to 4-bit oating point (FP4) remains challenging due to instability during optimization. We identify a fundamental sou
arXiv:2607.26788v1 Announce Type: cross Abstract: Clustered federated learning benefits from organizing heterogeneous participants into coalitions that train coalition-specific models, but such clustering is sustainable only if participants prefer their assigned coalition and the required transfers
arXiv:2607.24062v1 Announce Type: new Abstract: Reinforcement Learning (RL) training for Large Language Models (LLMs) often suffers from instability due to the discrepancy between training and inference. This training-inference discrepancy stems from two primary factors: an architectural separation
arXiv:2607.23821v1 Announce Type: new Abstract: Identifying therapeutic target genes from single-cell RNA sequencing (scRNA-seq) data remains a fundamental challenge in translational biology. Unlike bulk assays, scRNA-seq captures heterogeneous cellular states and rare subpopulations, but this same
arXiv:2607.20171v2 Announce Type: replace-cross Abstract: Learned solvers for compressible flow are usually compared to classical methods at equal mesh resolution rather than at equal computational cost, and they typically offer no guarantee that their solutions remain physically admissible. We pres
arXiv:2607.22752v1 Announce Type: cross Abstract: Face Image Quality Assessment (FIQA) aims to estimate the utility of facial images for reliable recognition. The evaluation of FIQA methods is predominantly based on the Error-versus-Discard Characteristic (EDC), which evaluates performance by progre
arXiv:2607.21647v1 Announce Type: new Abstract: Quantum federated learning enables distributed clients to train quantum neural networks without sharing local data, making it promising for privacy-aware intelligent services. Intelligent services in this context refer to privacy-sensitive distributed
arXiv:2607.18722v3 Announce Type: replace-cross Abstract: Asynchronous reinforcement learning improves throughput by decoupling rollout generation from optimization, but the resulting staleness is an inevitable byproduct, compounded jointly by policy lag, engine delays, and mixture-of-experts routin
arXiv:2603.18385v4 Announce Type: replace-cross Abstract: We present a new solution concept called evolutionarily stable Stackelberg equilibrium (SESS). We study the Stackelberg evolutionary game setting in which there is a single leading player and a symmetric population of followers. The leader se
arXiv:2607.19719v1 Announce Type: new Abstract: Latent world models improve sample efficiency in continuous control by optimizing policies over imagined latent trajectories, but common neural transitions offer limited direct control over modal persistence and error accumulation in long rollouts. We
arXiv:2510.10057v2 Announce Type: replace Abstract: The three-dimensional bin packing problem (3D-BPP) is widely applied in logistics and warehousing. Existing learning-based approaches often neglect practical stability-related constraints and exhibit limitations in generalizing across diverse bin d
arXiv:2607.19397v1 Announce Type: new Abstract: Deep Q-networks use target networks to stabilise bootstrapped value learning, but the standard hard copy update also introduces a tradeoff. Holding the target network fixed, improves short term stability, yet each hard update abruptly replaces the targ
arXiv:2605.11836v2 Announce Type: replace-cross Abstract: Lifelong Model Editing aims to continuously update evolving facts in Large Language Models while preserving unrelated knowledge and general capabilities, yet it remains plagued by catastrophic forgetting and model collapse. Empirically, we fi
arXiv:2607.19232v1 Announce Type: new Abstract: Hierarchical Reinforcement Learning (HRL) intends to separate strategic planning from primitive execution. It has been widely successful in solving long-horizon and complex tasks, where flat-RL algorithms have difficulty in learning. However, while the
arXiv:2607.18258v1 Announce Type: new Abstract: Reinforcement learning from human feedback (RLHF) with preference-based reward models often exhibits unstable training dynamics. A key contributing factor is that standard RLHF relies on a single sequence-level scalar reward, which is propagated to tok
arXiv:2607.18282v1 Announce Type: new Abstract: Bayesian Optimization is widely used for expensive black-box optimization, yet its success often depends on choosing a kernel that matches the objective's unknown structure. In this work, we propose ALAS, a flexible Gaussian Process kernel family built
arXiv:2607.18885v1 Announce Type: new Abstract: Kernel-based alignment of CLIP toward a vision centric teacher such as DINOv2 (KUEA) improves CLIP's visual representations while preserving text-encoder compatibility, using a fixed trade-off weight tuned on curated ImageNet-1K. We ask whether this tr
arXiv:2607.17526v1 Announce Type: cross Abstract: Zero-shot text-guided editing of real-world music recordings requires balancing semantic modification with faithful preservation of the original musical structure. Although recent diffusion transformers trained with rectified flow have achieved remar
arXiv:2605.29547v2 Announce Type: replace-cross Abstract: Deep learning optimization relies heavily on the assumption of smooth loss landscapes, a condition systematically violated by modern architectures due to non-smooth components such as ReLU activations and quantization operators. In such non-s
arXiv:2512.10279v5 Announce Type: replace-cross Abstract: We present an algorithm for computing evolutionarily stable strategies (ESSs) in symmetric perfect-recall extensive-form games of imperfect information. Our main algorithm is for two-player games, and we describe how it can be extended to mul
arXiv:2603.24002v3 Announce Type: replace Abstract: Physics-Informed Neural Networks (PINNs) for high-dimensional and high-order partial differential equations (PDEs) are primarily constrained by the $\mathcal{O}(d^k)$ spatial derivative complexity and the $\mathcal{O}(P)$ memory overhead of backpro
arXiv:2607.15623v1 Announce Type: cross Abstract: Predictive models deployed at scale influence future data, a phenomenon called performativity. And there is always one way to cope: Train the model on new data, deploy it again, and repeat. This process, called retraining or repeated risk minimizatio
arXiv:2607.14576v1 Announce Type: new Abstract: We propose \emph{the sublinear-growth principle} for deep residual architectures -- a sharp stability threshold on the input-magnitude exponent of every residual block's velocity field: $$\|v(x, t)\| \leq c\,\|x\|^q + b, \qquad q \in [0, 1].$$ The thre