Quantization, distillation, pruning and serving work aimed at the same accuracy for less memory, latency and money.
arXiv:2608. 05464v1 Announce Type: cross Abstract: The pruning of network connections is key to brain function but, despite its importance, there exist few biologically-plausible pruning rules with demonstrated good performance.
arXiv:2608. 06135v1 Announce Type: new Abstract: Large Language Models (LLMs) such as ChatGPT and Claude are widely used for information retrieval and problem-solving.
arXiv:2608. 06146v1 Announce Type: new Abstract: End-to-end document parsers provide a unified interface, but serialize page layouts and regional contents into one autoregressive sequence.
arXiv:2608. 06227v1 Announce Type: cross Abstract: Despite advances in artificial intelligence (AI) across multiple sectors, today's AI tools, including deep learning and generative AI, still fail when embedded into physical systems, such as robots and vehicles operating under real-world physical laws.
arXiv:2608. 05499v1 Announce Type: cross Abstract: Modern deep neural networks achieve strong performance, but their scale makes them costly and slow, especially on resource-constrained edge devices.
arXiv:2608. 05245v1 Announce Type: new Abstract: Reusable skills, which encapsulate the procedural knowledge required to solve real-world professional tasks, offer LLM-based agents a path toward self-evolution in expert domains.
arXiv:2604. 09297v3 Announce Type: replace-cross Abstract: Agent skills are increasingly used to configure coding agents for software engineering (SE) tasks, yet current practice treats them as static, hand-crafted assets, or evolved on pass rate alone.
arXiv:2608. 05734v1 Announce Type: new Abstract: Subliminal Learning (SL) is a surprising type of generalization displayed by modern language models.
arXiv:2608. 03228v2 Announce Type: replace Abstract: Existing low rank KV cache methods preserve either model weights or key variance, neither of which directly reflects the attention scores used during inference.
arXiv:2608. 05168v1 Announce Type: new Abstract: Large language models often fail on reasoning tasks despite possessing the capability to solve them.
arXiv:2608. 06150v1 Announce Type: new Abstract: Earth-surface monitoring requires change detection models capable of recognizing arbitrary semantic categories.
arXiv:2601. 07568v3 Announce Type: replace-cross Abstract: Diffusion large language models (dLLMs) offer capabilities beyond those of autoregressive (AR) LLMs, such as parallel decoding and random-order generation.
arXiv:2608. 06057v1 Announce Type: new Abstract: Tool-calling agents infer task state from accumulated dialogue and tool traces.
arXiv:2608. 05326v1 Announce Type: new Abstract: Autoregressive large language model inference is increasingly constrained by the memory footprint of the Key-Value (KV) cache.
arXiv:2608. 05253v1 Announce Type: new Abstract: Quantized orthogonal fine-tuning (qoft) enables parameter-efficient adaptation of low-bit language models by learning structured activation rotations before frozen quantized weights.
arXiv:2608. 05724v1 Announce Type: cross Abstract: Sparse word embedding pipelines can avoid dense co-occurrence matrix materialization, dense factorization, and gradient training while still relying on sparse global corpus statistics.
arXiv:2608. 05926v1 Announce Type: cross Abstract: Edge inference is a promising paradigm to provide large language model (LLM) inference services in next-generation mobile networks.
arXiv:2608. 05802v1 Announce Type: cross Abstract: On-Policy Distillation (OPD) is emerging as a promising alternative to reinforcement learning for LLM post-training, yet its effectiveness in multilingual settings remains underexplored.
arXiv:2608. 05219v1 Announce Type: new Abstract: Privileged on-policy distillation provides dense supervision for multi-turn agents by allowing a synchronized teacher to re-score the student's response at every turn with access to training-only references, such as successful trajectories.
arXiv:2608. 05240v1 Announce Type: cross Abstract: One-bit post-training quantization represents each weight using only its sign, requiring all deployment contexts to share the same binary weight matrix even when their activation statistics favor different sign patterns.