Quantization, distillation, pruning and serving work aimed at the same accuracy for less memory, latency and money.
arXiv:2606. 11556v1 Announce Type: cross Abstract: Continuous electrocardiography (ECG) monitoring could surface rhythm abnormalities before they escalate into cardiovascular events.
arXiv:2606. 11709v1 Announce Type: new Abstract: On-policy self-distillation (OPSD) provides dense, token-level supervision for reasoning models by aligning a model's own distribution with the distribution it produces under privileged context, typically a verified solution.
arXiv:2606. 11249v1 Announce Type: cross Abstract: Realizing the vision of 6G connected robotics requires reconciling high-performance collaborative control with the rigid spectral limitations of physical wireless channels.
arXiv:2606. 11605v1 Announce Type: cross Abstract: Predicting process-property relationships in manufacturing is often challenged by high experimental costs and the limited interpretability of complex 'black-box' models.
arXiv:2606. 12411v1 Announce Type: cross Abstract: Modern conversational agents condition on an ever-growing dialogue history at each turn, incurring redundant attention and encoding costs that grow with conversation length.
arXiv:2606. 11279v1 Announce Type: cross Abstract: Automatic speech recognition systems have been shown to under-perform when it comes to transcribing words rarely seen in the training data, namely specialized terminology.
arXiv:2606. 11836v1 Announce Type: cross Abstract: This paper presents a novel data-free and training-free compression approach for speech foundation models using channelwise clustering via k-means.
arXiv:2606. 11792v1 Announce Type: cross Abstract: Video Large Multimodal Models have achieved remarkable progress in video understanding, yet they remain prone to hallucinations, where generated responses are not faithfully supported by the input video.
arXiv:2606. 11853v1 Announce Type: cross Abstract: Multi-modal large language models (MLLMs) depend on in-context learning (ICL) for rapid task adaptation, but their scalability is severely limited by finite context windows and the growing cost of key-value (KV) caches in long multi-modal sequences.
arXiv:2606. 11357v1 Announce Type: cross Abstract: With the growing demand for on-device LLM inference, edge SoCs increasingly integrate NPUs to improve performance and energy efficiency under tight power and thermal budgets.
arXiv:2606. 11391v1 Announce Type: new Abstract: Tensor Product Representations provide the structural fidelity required for symbolic reasoning in models but suffer from exponential dimensionality growth when encoding deep recursive structures.
arXiv:2602. 10908v2 Announce Type: replace-cross Abstract: We present SoftMatcha 2, an ultra-fast and flexible search algorithm that enables search over trillion-scale natural language corpora in under 0.
arXiv:2606. 12412v1 Announce Type: cross Abstract: Vision-language models (VLMs) project images into hundreds to thousands of visual tokens, making decoder inference expensive in both attention computation and KV-cache memory.
arXiv:2606. 11751v1 Announce Type: cross Abstract: Multi-turn image editing is essential for iterative design, yet current models often struggle with identity drift and error accumulation over successive steps.
arXiv:2605. 15435v2 Announce Type: replace Abstract: Standard deep-learning pipelines usually choose the network architecture before training and keep it fixed throughout optimization.
arXiv:2606. 11627v1 Announce Type: cross Abstract: Recent work has shown that on-policy distillation can internalize privileged context, such as system prompts or task hints, into a student model so that the context is no longer needed at inference time.
arXiv:2606. 11339v1 Announce Type: cross Abstract: We study distributed optimization with stochastic gradients and finite-bit communication modeled by random (unbiased) quantization.
arXiv:2601. 23278v2 Announce Type: replace Abstract: Diffusion Large Language Models (DLLMs) offer a compelling alternative to Auto-Regressive models, but their deployment is constrained by high decoding cost.
arXiv:2606. 12370v1 Announce Type: new Abstract: Reinforcement learning (RL) has become a key component in modern large language models, yet the rollout stage remains the key bottleneck in RL training pipelines.
arXiv:2606. 12280v1 Announce Type: new Abstract: Post-training quantization lets large text-to-image diffusion transformers run on consumer GPUs, yet the hardware-specific trade-offs are seldom measured directly.