Quantization, distillation, pruning and serving work aimed at the same accuracy for less memory, latency and money.
arXiv:2606. 03070v1 Announce Type: cross Abstract: Asynchronous reinforcement learning can improve language-model post-training throughput by decoupling response generation from policy optimization, but stale responses introduce distribution drift.
arXiv:2606. 03026v1 Announce Type: cross Abstract: Spiking language models expose activation sparsity that dense Transformer runtimes do not directly exploit.
arXiv:2606. 03444v1 Announce Type: cross Abstract: Unifying the complementary strengths of diverse Vision Foundation Models (VFMs) into a single efficient model is highly desirable but challenged by the negative transfer inherent in monolithic distillation.
arXiv:2606. 03180v1 Announce Type: cross Abstract: Vision-language models (VLMs) for radiology have emerged as a scalable paradigm by leveraging image-report pairs naturally produced in clinical workflows.
arXiv:2603. 04956v2 Announce Type: replace Abstract: This paper considers the problem of converting a given dense linear layer to low precision.
arXiv:2606. 03939v1 Announce Type: cross Abstract: Federated Learning (FL) of foundation and edge models increasingly targets deployments where client data distributions drift over time, yet existing forgetting-mitigation methods assume each client's distribution is stationary.
arXiv:2606. 02955v1 Announce Type: cross Abstract: Diffusion large language models promise parallel token generation, yet inference remains bottlenecked by deciding which masked tokens can be safely committed together.
arXiv:2606. 03052v1 Announce Type: new Abstract: Knowledge Distillation (KD) is a powerful tool for model compression, yet the precise mechanisms by which student models acquire feature representations remain underexplored.
arXiv:2606. 03463v1 Announce Type: new Abstract: Conversational AI agents require memory systems that are both scalable and semantically coherent across long interaction horizons.
arXiv:2606. 03014v1 Announce Type: new Abstract: Mixture-of-Agents (MoA) systems improve reasoning accuracy by routing each query to multiple expert LLMs and aggregating their outputs.
arXiv:2606. 03269v1 Announce Type: new Abstract: Visual Question Answering (VQA) is the task of answering questions about images, requiring the integration of multimodal input and reasoning.
arXiv:2606. 02684v1 Announce Type: cross Abstract: On-Policy distillation (OPD) in large language models is shifting from full-trace KL supervision toward more selective training paradigms.
arXiv:2606. 03888v1 Announce Type: cross Abstract: Self-supervised learning has enabled large-scale pre-training on 2D natural images, producing general-purpose visual representations that transfer effectively across tasks.
arXiv:2606. 02634v1 Announce Type: cross Abstract: We introduce Echo-POSED, a self-supervised framework for real-time transthoracic echocardiography (TTE) guidance that recommends probe adjustments directly from 2D ultrasound images, without the need for expert-labelled views or tracked probe trajectories.
arXiv:2606. 02673v1 Announce Type: new Abstract: Graphs have been used to enhance large language models (LLMs) for structured reasoning, mostly as external knowledge sources are provided to models at test time.
arXiv:2606. 03645v1 Announce Type: cross Abstract: Large Language Models exhibit paradoxical fragility in fundamental arithmetic, implying a disconnect between internal computation and discrete output.
arXiv:2606. 02842v1 Announce Type: new Abstract: Multimodal spatial reasoning often relies on long chains of intermediate textual and visual thoughts, where accumulating visual tokens and dense cross-modal attention incur substantial computation and memory overhead.
arXiv:2602. 17063v2 Announce Type: replace-cross Abstract: Sub-bit model compression targets storage below one bit per weight; as magnitudes are aggressively compressed, the sign bit becomes a fixed-cost bottleneck.
arXiv:2512. 03627v2 Announce Type: replace Abstract: Despite rapid progress in large-scale language and vision models, AI agents still suffer from a fundamental limitation: they cannot remember.
arXiv:2606. 03553v1 Announce Type: cross Abstract: While principal component analysis (PCA) is a fundamental tool for dimensionality reduction, its dense representations make it ill-suited for high-dimensional data.