Quantization, distillation, pruning and serving work aimed at the same accuracy for less memory, latency and money.
arXiv:2606. 21401v2 Announce Type: replace-cross Abstract: Agentic AI applications compose multiple model calls and tool executions, creating new scheduling challenges for GPU-CPU clusters.
arXiv:2606. 29280v1 Announce Type: cross Abstract: We identify intervention bias as a previously unquantified failure mode of zero-shot large-language-model (LLM) educational advisory agents: without task-specific training, they recommend action when a hindsight-optimal oracle policy mandates inaction.
arXiv:2606. 29201v1 Announce Type: cross Abstract: Behavior-cloned policies often learn multiple behavior modes from demonstration datasets, including modes that are unsafe or otherwise undesired at deployment.
arXiv:2606. 30520v1 Announce Type: cross Abstract: Visual environments are a demanding setting for quantum reinforcement learning (QRL): high-dimensional observations, unstable RL optimisation, and constrained variational quantum circuits (VQCs) are difficult to train jointly.
arXiv:2606. 29581v1 Announce Type: cross Abstract: Modern LLM deployments routinely compress models and raise sampling temperature to reduce cost, latency, or repetition, yet safety evaluations usually treat these choices as fixed implementation details.
arXiv:2606. 30445v1 Announce Type: new Abstract: Online imitation learning (IL), particularly on-policy distillation, has emerged as a strong LLM post-training approach, often outperforming offline supervised fine-tuning (SFT).
arXiv:2606. 30292v1 Announce Type: new Abstract: We present DreamForge-World 0.
arXiv:2606. 29718v1 Announce Type: cross Abstract: Extensive context has become the norm as Large Language Models (LLMs) are increasingly deployed in long-horizon tasks.
arXiv:2505. 22391v2 Announce Type: replace-cross Abstract: Modeling physical systems in a generative manner offers several advantages, including the ability to handle partial observations, generate diverse solutions, and address both forward and inverse problems.
arXiv:2606. 30499v1 Announce Type: new Abstract: Federated Learning often suffers under non-independently and identically distributed data, where a single global model may fail to represent the diversity of client distributions.
arXiv:2606. 28446v1 Announce Type: cross Abstract: Light curves describe temporal variations in the brightness of celestial objects.
arXiv:2606. 29464v1 Announce Type: cross Abstract: Vision-language dataset distillation (VLDD) compresses a large image-text paired dataset into a small set of synthetic pairs that can efficiently train contrastive vision-language models under strict data and compute budgets.
arXiv:2604. 28123v3 Announce Type: replace-cross Abstract: The standard post-training recipe for large multimodal models (LMMs) applies supervised fine-tuning (SFT) on curated demonstrations followed by reinforcement learning with verifiable rewards (RLVR).
arXiv:2606. 29657v1 Announce Type: new Abstract: As AI systems become more capable, training procedures that optimize for downstream outcomes risk introducing implicit agency: goal-directed behavior that designers never specified.
arXiv:2605. 14252v2 Announce Type: replace-cross Abstract: Spiking neural networks (SNNs), which are brain-inspired and spike-driven, achieve high energy efficiency.
arXiv:2606. 28962v1 Announce Type: cross Abstract: Model quantization is essential for the efficient deployment of Large Language Models (LLMs), but introduces a critical vulnerability: Quantization-Conditioned Backdoor (QCB) attacks.
arXiv:2505. 12526v2 Announce Type: replace Abstract: Temporal graph networks suffer from irregular supervision in realworld dynamic graphs, as most minibatches contain few labeled events.
arXiv:2602. 19778v4 Announce Type: replace-cross Abstract: Automatic Chord Recognition (ACR) is constrained by the scarcity of aligned chord labels, as well-aligned annotations are costly to acquire.
arXiv:2606. 28529v1 Announce Type: cross Abstract: Embodied foundation models have recently been widely used to improve robot generalization and task success rates.
arXiv:2603. 25144v2 Announce Type: replace-cross Abstract: Dataset distillation (DD) compresses a large training set into a small synthetic set, reducing storage and training cost, and has shown strong results on general benchmarks.