This is the source code of our ICML25 paper, titled "Accelerating Large Language Model Reasoning via Speculative Search".
☆24Jun 1, 2025Updated last year
Alternatives and similar repositories for LLMReasoning-SpecSearch
Users that are interested in LLMReasoning-SpecSearch are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- This is the code for our ICLR 2025 paper, titled Computing Circuits Optimization via Model-Based Circuit Genetic Evolution.☆13May 27, 2025Updated last year
- The code of paper Sample-Efficient Reinforcement Learning via Conservative Model-Based Actor-Critic. Zhihai Wang, Jie Wang*, Qi Zhou, Bin…☆20May 26, 2022Updated 4 years ago
- The official repo of NeurIPS2025 Paper: High-Performance Arithmetic Circuit Optimization via Differentiable Architecture Search☆19Oct 19, 2025Updated 11 months ago
- A collection on the recent reproduction papers and projects on DeepSeek-R1☆31Feb 27, 2025Updated last year
- The code of paper *Learning Robust Policy against Disturbance in Transition Dynamics via State-Conservative Policy Optimization*.☆18Mar 26, 2022Updated 4 years ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- The code for "AttentionPredictor: Temporal Pattern Matters for Efficient LLM Inference", Qingyue Yang, Jie Wang, Xing Li, Zhihai Wang, Ch…☆29Jul 15, 2025Updated last year
- The code of paper Learning Cut Selection for Mixed-Integer Linear Programming via Hierarchical Sequence Model. Zhihai Wang, Xijun Li,…☆66May 12, 2023Updated 3 years ago
- This is the code of paper "De Novo Molecular Generation via Connection-aware Motif Mining". Zijie Geng, Shufang Xie, Yingce Xia, Lijun Wu…☆63Jan 7, 2025Updated last year
- ChiPBench:Benchmarking End-to-End Performance of AI-based Chip Placement Algorithms☆76Sep 22, 2025Updated last year
- The official repo of ICML2026 Paper: Adversarial Latent Embedding Repair for LLM Continual Learning☆19Aug 25, 2026Updated last month
- Must-read papers on Knowledge Graph Embedding☆30Oct 15, 2020Updated 5 years ago
- This is the code of DiffILO, an unsupervised learning approach for predicting solutions to Integer Linear Programs (ILPs).☆40Oct 24, 2025Updated 11 months ago
- This is the code of CoCo-MILP: Inter-Variable Contrastive and Intra-Constraint Competitive MILP Solution Prediction. AAAI 2026 Oral.☆16May 13, 2026Updated 5 months ago
- The code of paper "Learning Rule-Induced Subgraph Representations for Inductive Relation Prediction" in NeurIPS 2023.☆14Nov 25, 2023Updated 2 years ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Code for our paper: ACM-MILP: Adaptive Constraint Modification via Grouping and Selection for Hardness-Preserving MILP Instance Generatio…☆15Jan 3, 2025Updated last year
- ☆10Oct 5, 2023Updated 3 years ago
- [ICML 2025 Spotlight] RAPID: Long-Context Inference with Retrieval-Augmented Speculative Decoding☆22Mar 2, 2025Updated last year
- This repository collects various works that reproduce DeepSeek R1, as well as works related to DeepSeek R1 and the DeepSeek series.☆20Apr 27, 2025Updated last year
- AdaptiveStep: Automatically Dividing Reasoning Step through Model Confidence☆11Mar 2, 2025Updated last year
- USTC Resources☆22Sep 18, 2023Updated 3 years ago
- Official implementation of NeurIPS'24 paper "Reinforcement Learning Policy as Macro Regulator Rather than Macro Placer".☆21Aug 1, 2026Updated 2 months ago
- Official Implement for Paper "Neural Krylov Iteration for Accelerating Linear System Solving"☆16May 6, 2025Updated last year
- Pytorch implementation of our paper accepted by ICML 2023 -- "Bi-directional Masks for Efficient N:M Sparse Training"☆14Jun 7, 2023Updated 3 years ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- ☆18May 25, 2026Updated 4 months ago
- Must-read papers on Knowledge Graph Reasoning (KGR)☆21Mar 16, 2020Updated 6 years ago
- Here is the Feiyue handbook for all ECE students, including 1) how to prepare for your application, 2) official program organized by HUST…☆18Jun 6, 2020Updated 6 years ago
- The official repo for the paper "Optimizing LLM Inference Throughput via Memory-aware and SLA-constrained Dynamic Batching"☆17Mar 17, 2025Updated last year
- Cross-Self KV Cache Pruning for Efficient Vision-Language Inference☆10Dec 15, 2024Updated last year
- Coco is a proactive co-assistant that connects user workspace with a broader ecosystem of AI agents.☆39Sep 23, 2026Updated 3 weeks ago
- Accelerating Large-Scale Reasoning Model Inference with Sparse Self-Speculative Decoding☆121Dec 2, 2025Updated 10 months ago
- BESA is a differentiable weight pruning technique for large language models.☆17Mar 4, 2024Updated 2 years ago
- ☆18Feb 4, 2026Updated 8 months ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- Pytorch code of [CVPR 2023] "NAR-Former: Neural Architecture Representation Learning towards Holistic Attributes Prediction".☆12Mar 14, 2023Updated 3 years ago
- ☆16Jan 14, 2025Updated last year
- ☆16Jan 12, 2026Updated 9 months ago
- channel pruning for accelerating very deep neural networks☆13Mar 8, 2021Updated 5 years ago
- [NeurIPS 2026] When and How Much to Imagine: Adaptive Test-Time Scaling with World Models for Visual Spatial Reasoning☆20Sep 29, 2026Updated 2 weeks ago
- This is the official Python version of CoreInfer: Accelerating Large Language Model Inference with Semantics-Inspired Adaptive Sparse Act…☆20Oct 25, 2024Updated last year
- Interpretable Contrastive Monte Carlo Tree Search Reasoning☆52Nov 9, 2024Updated last year