Quantization, distillation, pruning and serving work aimed at the same accuracy for less memory, latency and money.
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. 08696v1 Announce Type: cross Abstract: Counterfactual recourse aims to provide actionable feature changes that would alter an unfavorable decision made by a predictive model.
arXiv:2601. 21149v3 Announce Type: replace-cross Abstract: Recent progress in geospatial foundation models highlights the importance of learning general-purpose representations for real-world locations, particularly points-of-interest (POIs) where human activity concentrates.
arXiv:2605. 15491v2 Announce Type: replace-cross Abstract: Layer pruning removes entire Transformer decoder blocks from large language models, but introduces a mismatch between the hidden state received by the next surviving layer and the distribution it was trained to process, leading to significant performance degradation.
arXiv:2605. 13768v2 Announce Type: replace-cross Abstract: This is the second part of the work investigating quantized matrix multiplication (MatMul).
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. 09091v1 Announce Type: new Abstract: On-policy distillation (OPD) has recently emerged as an important post-training paradigm.
arXiv:2606. 07819v1 Announce Type: new Abstract: Recently, the efficiency of Large Language Models (LLMs) deployment has become a critical concern in practical applications.
arXiv:2606. 08953v1 Announce Type: new Abstract: Modern generative models often define an entire probability path from a simple prior to the data law, rather than only an endpoint map.
arXiv:2606. 07690v1 Announce Type: cross Abstract: Finetuning data selection requires balancing two competing goals: selecting examples that improve the downstream objective, and doing so without repeatedly finetuning models.
arXiv:2606. 09572v1 Announce Type: cross Abstract: Vision-language-action models have shown strong promise for robot manipulation, yet raw language is primarily needed to specify task intent rather than to be repeatedly processed during high-frequency low-level execution.
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. 07710v1 Announce Type: cross Abstract: The autoregressive nature of large language models (LLMs) remains a significant bottleneck for inference, particularly in complex agentic workloads.
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. 08594v1 Announce Type: new Abstract: Deep learning EEG denoising architectures have scaled from tens of thousands to tens of millions of parameters, yet no prior study has isolated model capacity as the experimental variable or tested whether reconstruction metrics predict downstream neural-signal utility.
arXiv:2606. 08156v1 Announce Type: cross Abstract: Vision Transformers (ViTs) achieve strong performance but suffer from high computational costs due to quadratic self-attention complexity.
arXiv:2606. 07836v1 Announce Type: cross Abstract: Many-body GW-Bethe-Salpeter equation calculations are essential for accurate simulations of electronic structure and optical properties in modern low-dimensional nanomaterials.
arXiv:2606. 09514v1 Announce Type: new Abstract: Large language models (LLMs) incur high inference cost due to their depth and parameter scale.
arXiv:2606. 08051v1 Announce Type: new Abstract: Financial transaction processing requires extracting structured merchant information from noisy, abbreviated bank transaction strings at scale.
arXiv:2605. 18856v3 Announce Type: replace Abstract: Long-context inference is increasingly constrained by the KV cache: resident memory grows with context length, and decoding becomes limited by repeated High Bandwidth Memory (HBM) streaming rather than arithmetic.