Preprint2025
SFT Memorizes, RL Generalizes
Unknown
RL improves generalization in text and visual tasks while SFT primarily memorizes training data, with inference-time compute scaling further enhancing RL gains.
0Jan 1, 2025Scaling Laws
AI Research
AI & ML Research Papers
A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
All Papers
28 papersPreprint2023
FastViT
Unknown
FastViT introduces RepMixer, a reparameterized token mixer, achieving fast inference with minimal accuracy loss in hybrid vision transformers.
0Mar 1, 2023TransformersComputer Vision
arXiv
Preprint2022
EfficientFormer
Unknown
EfficientFormer revisits ViT design principles through latency analysis, identifies inefficient operators, and proposes a dimension-consistent design with a latency-driven slimming method for faster inference.
0Jun 1, 2022TransformersComputer Vision
Preprint2021
LeViT
Unknown
LeViT is a hybrid vision transformer optimized for fast inference, achieving superior speed-accuracy tradeoffs over convnets and ViTs.
0Apr 1, 2021Neural Networks
arXiv
Preprint2025
Sarvam - M
Unknown
A large language model built on Mistral Small, enhanced with SFT, RLVR, and inference optimization for Indian languages and reasoning tasks.
0May 1, 2025Large Language ModelsReinforcement Learning
Preprint2023
Mistral 7B
Unknown
Mistral 7B introduces grouped-query attention and sliding window attention to achieve faster inference and handle arbitrary-length sequences at reduced cost.
0Oct 1, 2023Attention Mechanisms
Preprint2020
FastBERT
Unknown
FastBERT introduces a speed-tunable encoder with adaptive inference time by adding early-exit branches at each transformer layer.
0Apr 1, 2020Transformers
Preprint2026
Fastkv: Decoupling of context reduction and kv cache compression for prefill-decoding acceleration
Unknown
FastKV decouples context reduction from KV cache compression to accelerate both prefill and decoding phases in LLM inference.
0Jan 1, 2026
Preprint2023
Fast inference from transformers via speculative decoding
Unknown
Introduces speculative decoding, an algorithm for faster sampling from autoregressive models by computing multiple tokens in parallel without altering outputs.
0Jan 1, 2023Transformers
Preprint2024
Unlocking efficiency in large language model inference: A comprehensive survey of speculative decoding
Unknown
A comprehensive survey of speculative decoding techniques for efficient large language model inference.
0Jan 1, 2024Large Language Models
Preprint2021
Mqbench: Towards reproducible and deployable model quantization benchmark
Yuhang Li, Mingzhu Shen, Yan Ren, et al.
Mqbench provides a reproducible and deployable benchmark for model quantization to accelerate deep learning inference.
71Jan 1, 2021BenchmarksQuantization
arXiv
Preprint2026
OpenForgeRL: Train Harness-native Agents in Any Environment
Xiao Yu, Baolin Peng, Ruize Xu, et al.
OpenForgeRL is an open-source framework that enables end-to-end training of harness-based AI agents in any environment by decoupling training and inference via a lightweight proxy and Kubernetes orchestrator.
0Jul 23, 2026MultimodalReasoning
arXiv