Quantization, distillation, pruning and serving work aimed at the same accuracy for less memory, latency and money.
arXiv:2608. 01676v1 Announce Type: cross Abstract: Sparse attention is widely deployed in long-context serving stacks, yet no framework audits how discarding blocks changes the influence of specific content on model output.
arXiv:2608. 01662v1 Announce Type: cross Abstract: DeepSeek Sparse Attention (DSA) enables efficient long-context modeling through its Lightning Indexer.
arXiv:2606. 21633v2 Announce Type: replace Abstract: The KV cache dominates GPU memory in long-context LLM serving, crowding out batch capacity and leaving GPU compute idle.
arXiv:2608. 01536v1 Announce Type: cross Abstract: Large Language Models (LLMs) increasingly rely on sparsity to reduce inference cost, but most prior work targets a single sparsity source-either weight or activation-and optimizes for batched multi-user inference.
arXiv:2608. 01428v1 Announce Type: cross Abstract: Embodied agents replan frequently to recover from execution drift, partial observability, and coordination hazards, but each LLM-based replanning call can consume an accumulated textual context that grows over time and across agents.
arXiv:2608. 00720v1 Announce Type: cross Abstract: Mapping neural networks to FPGAs enables low-latency, energy-efficient inference, particularly for lookup table (LUT)-based models that eliminate multipliers and map directly to reconfigurable fabric.
arXiv:2608. 00101v1 Announce Type: cross Abstract: AI coding agents like GitHub Copilot, Claude Code, and Codex interleave multi-step LLM inference with tool execution, creating a workload different from chatbots.
arXiv:2608. 00916v1 Announce Type: cross Abstract: Modern reranking recipes---billion-scale cross-encoders, mixture-of-experts (MoE) backbones, and distillation against strong teachers---have outpaced the training infrastructure available to most academic groups.
arXiv:2608. 00621v1 Announce Type: new Abstract: Multimodal-attributed graphs (MAGs), whose nodes carry heterogeneous attributes such as text and images over a relational structure, have become a fundamental substrate for label-free entity grouping tasks, including community discovery and product segmentation.
arXiv:2608. 00029v1 Announce Type: cross Abstract: The performance of deep learning models at scale relies heavily on how effectively high-level mathematical operations are mapped to underlying physical hardware.
arXiv:2608. 01953v1 Announce Type: cross Abstract: On-policy distillation (OPD) provides teacher supervision on states visited by the student, reducing the distribution gap between training and inference.
arXiv:2608. 02229v1 Announce Type: new Abstract: Classical neural networks frequently produce overconfident predictions on ambiguous or out-of-distribution (OOD) data, a liability that grows with each AI system deployed in safety-critical real-world scenarios.
arXiv:2607. 18082v3 Announce Type: replace Abstract: Rubric-based RL has recently shown promise in improving LLMs on open-ended tasks.
arXiv:2605. 28149v2 Announce Type: replace Abstract: Sparse Autoencoders (SAEs) extract interpretable features from Large Language Model activations, but standard variants enforce non-negative latents, so a bidirectional semantic axis (e.
arXiv:2608. 01285v1 Announce Type: new Abstract: The continued development of LLMs toward persistent and adaptive intelligence increasingly requires long-term memory mechanisms that preserve and reuse information across interactions.
arXiv:2608. 01745v1 Announce Type: new Abstract: Maximizing throughput under proportional fairness in dense wireless networks requires jointly managing user association, scheduling, base station (BS) activation, and handover control under hard finite-horizon energy and handover budgets, which induces a fundamental tension between BS-side energy management and user-side handover regulation.
arXiv:2608. 02034v1 Announce Type: new Abstract: Multi-step returns accelerate reward propagation in off-policy reinforcement learning, but couple the evaluation of each decision to the suboptimal logged actions that follow it, inducing a pessimistic bias that grows with the horizon.
arXiv:2502. 17055v5 Announce Type: replace Abstract: Training instability in modern deep learning systems is frequently triggered by rare but extreme gradient-norm spikes, which can induce oversized parameter updates, corrupt optimizer state, and lead to slow recovery or divergence.
arXiv:2608. 02139v1 Announce Type: cross Abstract: Large language models (LLMs) capable of self-improvement require not only effective policy optimization, but also a principled mechanism for transforming transient interaction experience into persistent model capabilities.
arXiv:2608. 01804v1 Announce Type: new Abstract: Post-training large language models (LLMs) via reinforcement learning (RL) has significantly advanced code generation capabilities.