Quantization, distillation, pruning and serving work aimed at the same accuracy for less memory, latency and money.
arXiv:2605. 27441v2 Announce Type: replace-cross Abstract: Query understanding in large-scale industrial search systems is typically implemented as a cascade of disparate, task-specific components.
arXiv:2411. 16102v2 Announce Type: replace Abstract: Offline batch inference, which leverages the flexibility of request batching to achieve higher throughput and lower costs, is becoming more popular for latency-insensitive applications.
arXiv:2606. 07924v1 Announce Type: cross Abstract: This paper presents our system description for the 2nd Workshop on Multimodal Augmented Generation via MultimodAl Retrieval (MAGMaR).
arXiv:2606. 07703v1 Announce Type: cross Abstract: Long-context prefill remains expensive because full/GQA layers still score the historical sequence, even in hybrid models with local, sparse, linear, or recurrent components.
arXiv:2606. 07618v1 Announce Type: cross Abstract: NVFP4 is a recently introduced hardware-supported FP4 format that improves the fidelity of 4-bit quantization through fine-grained block scales.
arXiv:2606. 07878v1 Announce Type: new Abstract: The KV cache is the memory bottleneck of long-horizon language model deployment.
arXiv:2603. 05500v2 Announce Type: replace-cross Abstract: Efficient and stable training of large language models (LLMs) remains a core challenge in modern machine learning systems.
arXiv:2602. 14033v1 Announce Type: cross Abstract: Future sixth-generation (6G) mobile networks will demand artificial intelligence (AI) agents that are not only autonomous and efficient, but also capable of real-time adaptation in dynamic environments and transparent in their decisionmaking.
arXiv:2606. 09508v1 Announce Type: new Abstract: Existing sparse attention and KV cache compression methods for long-context LLM inference typically apply fixed sparsity patterns or uniform budgets across all attention heads, overlooking the substantial variation in attention behavior among heads and contexts.
arXiv:2606. 09348v1 Announce Type: new Abstract: Long-horizon agentic tasks pose a fundamental credit assignment challenge for outcome-base reinforcement learning: trajectory-level rewards verify final correctness but provide limited guidance on which intermediate reasoning steps or tool interactions contribute to the outcome.
arXiv:2606. 09447v1 Announce Type: new Abstract: We present AliyunConsoleAgent, a web agent framework for automated documentation verification in real-world cloud consoles.
arXiv:2606. 08602v1 Announce Type: cross Abstract: We present an online reinforcement learning (RL) algorithm for fine-tuning flow-matching policies in continuous-control problems.
arXiv:2512. 07355v2 Announce Type: replace Abstract: Two traditions of interpretability have evolved side by side but seldom spoken to each other: Concept Bottleneck Models (CBMs), which prescribe what a concept should be, and Sparse Autoencoders (SAEs), which discover what concepts emerge.
arXiv:2605. 17289v2 Announce Type: replace-cross Abstract: Unstructured sparsity is now natively accelerated by recent GPU kernels and dataflow hardware, shifting the bottleneck from inference execution to the pruning algorithm.
arXiv:2606. 08850v1 Announce Type: cross Abstract: Inference-Time Scaling (ITS) has largely succeeded in verifiable domains like math and coding, where cheap verification enables scalable output selection.
arXiv:2606. 09059v1 Announce Type: cross Abstract: Two-stage post-training -- a Stage-1 warm-start (supervised fine-tuning, SFT, or on-policy distillation, OPD) followed by Stage-2 reinforcement learning (RL) -- is increasingly used for vision-language models (VLMs).
arXiv:2605. 13768v2 Announce Type: replace-cross Abstract: This is the second part of the work investigating quantized matrix multiplication (MatMul).
arXiv:2606. 09605v1 Announce Type: new Abstract: Foundation models offer a promising route to compress multi-modal physiological signals into compact representations of human health, with broad applications across sleep medicine, cardiology, neurology and other healthcare domains.
arXiv:2606. 08735v1 Announce Type: new Abstract: Quality-diversity reinforcement learning (QD-RL) aims to construct policy repertoires that contain both high-performing and behaviorally diverse policies.
arXiv:2510. 03389v2 Announce Type: replace-cross Abstract: Current quantum computers require algorithms that use limited resources economically.