Quantization, distillation, pruning and serving work aimed at the same accuracy for less memory, latency and money.
arXiv:2607. 05902v1 Announce Type: cross Abstract: Chamber music, as a highly precise multi-part interactive system, contains a logic of "role assignment and dynamic interaction" that provides an extremely valuable blueprint for exploring human-computer collaborative composition paradigms.
arXiv:2607. 05475v1 Announce Type: cross Abstract: Deploying Large Language Models (LLMs) on mobile devices enhances privacy and reduces latency, but is severely bottlenecked by hardware inefficiency.
arXiv:2607. 05468v1 Announce Type: cross Abstract: World Action Models (WAMs) have shown strong potential for robotic manipulation by jointly modeling visual future dynamics and executable action sequences.
arXiv:2607. 05457v1 Announce Type: cross Abstract: Deep neural networks often contain substantial hidden-state redundancy, but most compression methods operate directly on weights, neurons, or quantised representations without explicitly characterising the dynamical role of internal states.
arXiv:2607. 05399v1 Announce Type: cross Abstract: Large language model serving is increasingly limited by KV-cache growth under long-context workloads, yet existing KV-cache compression techniques are difficult to compare because they were evaluated on different models, tasks, budgets, and serving stacks.
arXiv:2607. 06326v1 Announce Type: new Abstract: Large language models deployed in open-world applications require safety guardrails that are both robust to complex risks and efficient enough for low-latency runtime moderation.
arXiv:2508. 16560v4 Announce Type: replace-cross Abstract: Sparse Autoencoders (SAEs) extract features from LLM internal activations, meant to correspond to interpretable concepts.
arXiv:2410. 11378v3 Announce Type: replace-cross Abstract: Personalized collaborative learning in federated settings faces a critical trade-off between customization and participant trust.
arXiv:2601. 01484v2 Announce Type: replace Abstract: Knowledge Distillation (KD) is a central paradigm for transferring knowledge from a large teacher network to a typically smaller student model, often by leveraging soft probabilistic outputs.
arXiv:2607. 06370v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have emerged as a promising approach for generalizable robotic manipulations.
arXiv:2607. 05804v1 Announce Type: new Abstract: On-policy distillation (OPD) trains a student policy by matching a stronger teacher on the student's own trajectories, offering a promising framework for language agent training.
arXiv:2607. 05711v1 Announce Type: new Abstract: Diffusion models have become a dominant paradigm for high-quality generative modeling, while post-training is essential for adapting them to diverse downstream applications.
arXiv:2607. 05471v1 Announce Type: cross Abstract: We present KAT-Coder-V2.
arXiv:2607. 05400v1 Announce Type: cross Abstract: Generative AI models, such as Large Language Models (LLMs) and diffusion models, have demonstrated impressive performance across a wide range of tasks.
arXiv:2605. 18419v2 Announce Type: replace-cross Abstract: Vision-language models (VLMs) can couple visual perception with open-ended clinical reasoning, making them attractive for computational histopathology.
arXiv:2607. 06481v1 Announce Type: cross Abstract: We present PACR-Video, a parameter-efficient framework for multi-shot long video extrapolation that preserves recurring entities, scene structure, visual style, and causal progression without full generator fine-tuning.
arXiv:2504. 20198v2 Announce Type: replace-cross Abstract: This work presents a comprehensive evaluation of neural network graph compilers across heterogeneous hardware platforms, addressing the critical gap between theoretical optimization techniques and practical deployment scenarios.
arXiv:2607. 05734v1 Announce Type: cross Abstract: Chain-of-thought (CoT) distillation in the recommendation domain is a necessary precursor to RL training, but raw teacher traces are ill-suited to this task.
arXiv:2607. 06114v1 Announce Type: cross Abstract: Diffusion and flow matching models generate high-quality samples, but their ODE samplers often need tens to hundreds of neural function evaluations (NFEs).
arXiv:2510. 07364v4 Announce Type: replace Abstract: What do thinking language models learn during training that their base models lack?