Quantization, distillation, pruning and serving work aimed at the same accuracy for less memory, latency and money.
arXiv:2510. 18383v3 Announce Type: replace-cross Abstract: Distilling the tool-use capabilities of large language models (LLMs) into small language models (SLMs) is essential for their practical application.
arXiv:2402. 14035v4 Announce Type: replace-cross Abstract: Knowledge distillation from foundation models to compact domain models is challenging due to substantial gaps in capacity, architecture, and modality.
arXiv:2606. 19558v1 Announce Type: new Abstract: Fidelity metrics, such as per-token KL divergence (KLD) against a high-precision reference, are often used in practice as low-cost proxies for benchmark quality.
arXiv:2603. 15106v2 Announce Type: replace Abstract: Enabling efficient deep neural network (DNN) inference on edge devices with different hardware constraints is a challenging task that typically requires DNN architectures to be specialized for each device separately.
arXiv:2605. 31393v2 Announce Type: replace-cross Abstract: Sign language translation (SLT) remains constrained by the limited availability of paired sign-video/text corpora and by the heavy-tailed vocabularies typical of real-world datasets.
arXiv:2602. 22495v3 Announce Type: replace-cross Abstract: Reinforcement learning (RL) post-training has recently driven major gains in long chain-of-thought reasoning large language models (LLMs), but the high inference cost of such models motivates distillation into smaller students.
arXiv:2606. 20474v1 Announce Type: cross Abstract: Context-heavy agents place unusual pressure on the key-value (KV) cache: long prefixes are reused across many short turns, while concurrency determines whether the serving system can keep GPUs utilized.
arXiv:2606. 20005v1 Announce Type: cross Abstract: Attention distillation, which trains one attention distribution to match another by minimizing their Kullback-Leibler (KL) divergence, is widely used in knowledge distillation, model compression, continual learning, and sparse-attention LLM training.
arXiv:2606. 20381v1 Announce Type: new Abstract: FP4 training promises substantial reductions in memory and computation cost for LLM pretraining, yet current FP4 hardware paths and recipes, including NVIDIA Blackwell/Rubin-class systems and AMD MI350-series GPUs, remain centered on E2M1 data elements.
arXiv:2606. 19348v1 Announce Type: cross Abstract: We present a preview version of DeepSeek-V4 series, including two strong Mixture-of-Experts (MoE) language models -- DeepSeek-V4-Pro with 1.
arXiv:2606. 19632v1 Announce Type: cross Abstract: Multi-agent reinforcement learning (MARL) enables agents to develop coordination strategies through emergent communication, but neural policies lack the formal safety guarantees required for safety-critical robotic deployment in drone swarms and autonomous vehicle fleets.
arXiv:2606. 19382v1 Announce Type: cross Abstract: While LLM-powered agents offer end-to-end automation for industrial asset lifecycles, real-world Industry 4.
arXiv:2604. 00626v4 Announce Type: replace Abstract: As Large Language Models continue to grow in both capability and cost, transferring frontier capabilities into smaller, deployable students has become an important engineering problem, and knowledge distillation remains a common technique for this transfer.
arXiv:2510. 18784v3 Announce Type: replace Abstract: Despite significant work on low-bit quantization-aware training (QAT), there is still an accuracy gap between such techniques and native training.
arXiv:2606. 20537v1 Announce Type: new Abstract: Mainstream LLM serving systems reuse prefix work mainly through paged or radix key-value (KV) caches.
arXiv:2606. 20053v1 Announce Type: new Abstract: The Doyle-Fuller-Newman (DFN) model resolves internal electrochemical states in lithium-ion batteries with high fidelity.
arXiv:2606. 19363v1 Announce Type: new Abstract: The deployment of Time-Series Foundation Models (TSFMs) in physical sciences is hindered by a critical trade-off: while these models encode rich, universal temporal dynamics, they suffer from severe distributional misalignment when applied zero-shot to specific scientific domains, and their computational cost prohibits deployment in edge-computing sensor networks.
arXiv:2606. 19364v1 Announce Type: new Abstract: The prefill stage of Large Language Model (LLM) inference is a growing contributor to cloud-scale energy cost.
arXiv:2606. 18967v1 Announce Type: new Abstract: Reinforcement learning (RL) has become a representative post-training paradigm for LLMs, enabling strong reasoning and agentic capabilities.
arXiv:2606. 18691v1 Announce Type: new Abstract: Pre-trained materials foundation models, or machine learning interatomic potentials, leverage general physicochemical knowledge to effectively approximate potential energy surfaces.