Quantization, distillation, pruning and serving work aimed at the same accuracy for less memory, latency and money.
arXiv:2605. 03217v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly deployed in settings that require nuanced ethical reasoning, yet existing bias evaluations treat model outputs as simply "biased" or "unbiased.
arXiv:2606. 05737v1 Announce Type: cross Abstract: Diffusion-based vision-language-action (VLA) models often inherit the image-generation view: actions are generated by iterative denoising.
arXiv:2606. 06034v1 Announce Type: new Abstract: Matrix inversion in chunk-wise parallel linear attention is a major bottleneck for long-context modeling, particularly on NPUs, where forward-substitution-based methods exhibit limited parallelism and poor hardware utilization.
arXiv:2606. 06302v1 Announce Type: new Abstract: Multi-turn Large Language Model (LLM) serving is critical for consistent user experiences, yet the linear growth of the Key-Value (KV) cache imposes significant pressure on GPU memory and bandwidth.
arXiv:2604. 23466v2 Announce Type: replace Abstract: NVIDIA's CUDA Tile (CuTile) introduces a Python-based, tile-centric abstraction for GPU kernel development that aims to simplify programming while retaining Tensor Core and Tensor Memory Accelerator (TMA) efficiency on modern GPUs.
arXiv:2601. 18383v2 Announce Type: replace-cross Abstract: Large Reasoning Models (LRMs) excel at solving complex problems by explicitly generating a reasoning trace before deriving the final answer.
arXiv:2606. 05232v1 Announce Type: new Abstract: Efficient multimodal foundation models often rely on manually designed token-reduction operators, such as pruning, merging, pooling, and adaptive reweighting.
arXiv:2606. 06467v1 Announce Type: cross Abstract: Long-context inference in modern LLMs is increasingly constrained by decoding efficiency, especially in reasoning-heavy settings where models generate long intermediate chains of thought.
arXiv:2508. 19006v2 Announce Type: replace-cross Abstract: This study investigates the pre-trained RNN attention models with the mainstream attention mechanisms, such as additive attention, Luong's three attentions, global self-attention and sliding window sparse attention, for the empirical asset pricing research on the top 420 large-cap US stocks.
arXiv:2606. 05597v1 Announce Type: new Abstract: Training vision-language web agents with multi-step RL is compute-intensive, with two dominant forms of inefficiency: idle GPUs in synchronous RL, and trajectories that use more steps and tokens than necessary.
arXiv:2606. 05860v1 Announce Type: new Abstract: Designing neural architectures for time-series forecasting and anomaly detection remains a resource-intensive task that often requires substantial domain expertise.
arXiv:2606. 06010v1 Announce Type: new Abstract: Long-term time series forecasting benefits from inductive biases that expose recurring temporal structure.
arXiv:2606. 06021v1 Announce Type: new Abstract: On-policy distillation (OPD) supervises the student only in output space by matching next-token probabilities.
arXiv:2606. 06474v1 Announce Type: cross Abstract: Discrete diffusion language models generate text by iteratively denoising an entire response in parallel.
arXiv:2605. 18848v3 Announce Type: replace Abstract: This paper introduces Exact Linear Attention (ELA), a mechanism that achieves linear computational complexity for Transformer attention by exploiting the exact decomposition property of kernel functions, thereby eliminating approximation error.
arXiv:2412. 11800v4 Announce Type: replace Abstract: Extracting anomaly causality facilitates diagnostics once monitoring systems detect system faults.
arXiv:2605. 25582v2 Announce Type: replace Abstract: Reinforcement learning for large language models faces a fundamental trade-off between sample efficiency and asymptotic performance: strictly on-policy methods discard trajectories after a single update, while off-policy reuse introduces distribution mismatch that existing trust-region techniques mitigate primarily by enforcing conservative optimization, often leaving rich training signals underutilized.
arXiv:2606. 06447v1 Announce Type: cross Abstract: Large language models often improve reasoning by generating explicit chain-of-thought (CoT), demonstrating the importance of intermediate computation.
arXiv:2606. 05538v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) models achieve strong performance through conditional computation, but their large parameter footprint poses deployment challenges.
arXiv:2606. 05988v1 Announce Type: new Abstract: Reasoning models produce long chain-of-thought traces that are costly to distill and encourage verbose student outputs.