yueliu1999 / Awesome-Efficient-Inference-for-LRMsLinks
Awesome-Efficient-Inference-for-LRMs is a collection of state-of-the-art, novel, exciting, token-efficient methods for Large Reasoning Models (LRMs). It contains papers, codes, datasets, evaluations, and analyses. https://arxiv.org/pdf/2503.23077
β230Updated 4 months ago
Alternatives and similar repositories for Awesome-Efficient-Inference-for-LRMs
Users that are interested in Awesome-Efficient-Inference-for-LRMs are comparing it to the libraries listed below
Sorting:
- [NeurIPS 2025π₯]Main source code of SRPO framework.β176Updated last month
- [NeurIPS2024] Twin-Merging: Dynamic Integration of Modular Expertise in Model Mergingβ138Updated 7 months ago
- β123Updated last month
- β105Updated 4 months ago
- [ACL'25] Code for "Aligning Large Language Models to Follow Instructions and Hallucinate Less via Effective Data Filtering"β20Updated 3 months ago
- [ICML2025] Make LoRA Great Again: Boosting LoRA with Adaptive Singular Values and Mixture-of-Experts Optimization Alignmentβ133Updated 4 months ago
- Explain Before You Answer: A Survey on Compositional Visual Reasoningβ287Updated last week
- Official Repository for Paper: The Curse of CoT: On the Limitations of Chain-of-Thought in In-Context Learningβ51Updated 6 months ago
- [Arxiv 2024] Official code for Decomposing the Neurons: Activation Sparsity via Mixture of Experts for Continual Test Time Adaptationβ70Updated last year
- [ICML 2025] "SepLLM: Accelerate Large Language Models by Compressing One Segment into One Separator"β551Updated 2 months ago
- Tree Search for LLM Agent Reinforcement Learningβ229Updated 3 weeks ago
- Selective Prompt Anchoringβ93Updated this week
- β354Updated 4 months ago
- Official repository for InfiGUI-G1. We introduce Adaptive Exploration Policy Optimization (AEPO) to overcome semantic alignment bottlenecβ¦β110Updated last month
- Code for "Teaching Large Language Models to Maintain Contextual Faithfulness via Synthetic Tasks and Reinforcement Learning"β39Updated 3 months ago
- RAS: Retrieval-And-Structuring for Knowledge-Intensive LLM Generationβ56Updated last month
- EmoBench-M: A benchmark for evaluating Emotional Intelligence in Multimodal Large Language Models.β118Updated last week
- [NIPS'25 Spotlight] Mulberry, an o1-like Reasoning and Reflection MLLM Implemented via Collective MCTSβ1,221Updated last month
- β195Updated 2 weeks ago
- [ICCVβ25] Official implementation of paper "Towards Performance Consistency in Multi-Level Model Collaboration"β42Updated last month
- Autoregressive Semantic Visual Reconstruction Helps VLMs Understand Betterβ176Updated 4 months ago
- ScaleCUA is the open-sourced computer use agents that can operate on corss-platform environments (Windows, macOS, Ubuntu, Android).β709Updated 3 weeks ago
- β46Updated 7 months ago
- **Deep Video Discovery (DVD)** is a deep-research style question answering agent designed for understanding extra-long videos.β289Updated last week
- [Neurips 2025] R-KV: Redundancy-aware KV Cache Compression for Reasoning Modelsβ1,138Updated last week
- DPO-Shift: Shifting the Distribution of Direct Preference Optimizationβ60Updated 7 months ago
- MarkDiffusion: An Open-Source Toolkit for Generative Watermarking of Latent Diffusion Modelsβ139Updated last week
- β12Updated 8 months ago
- JittorGeometric is a Jittor-based graph machine learning library.β322Updated 2 months ago
- (ICCV-2025 Official Code)) Improving Generalist Model with Domain-Specific Expertsβ85Updated 3 months ago