xiaomi-research / colarLinks
[arXiv2505] Think Silently, Think Fast: Dynamic Latent Compression of LLM Reasoning Chains
☆50Updated last month
Alternatives and similar repositories for colar
Users that are interested in colar are comparing it to the libraries listed below
Sorting:
- ACL'2025: SoftCoT: Soft Chain-of-Thought for Efficient Reasoning with LLMs. and preprint: SoftCoT++: Test-Time Scaling with Soft Chain-of…☆46Updated 3 months ago
- [ICML 2025] M-STAR (Multimodal Self-Evolving TrAining for Reasoning) Project. Diving into Self-Evolving Training for Multimodal Reasoning☆69Updated 2 months ago
- CoT-Valve: Length-Compressible Chain-of-Thought Tuning☆85Updated 7 months ago
- NoisyRollout: Reinforcing Visual Reasoning with Data Augmentation☆88Updated last month
- A Self-Training Framework for Vision-Language Reasoning☆84Updated 8 months ago
- Official Repository of LatentSeek☆60Updated 3 months ago
- Laser: Learn to Reason Efficiently with Adaptive Length-based Reward Shaping☆55Updated 4 months ago
- ☆46Updated 5 months ago
- This repo contains evaluation code for the paper "MileBench: Benchmarking MLLMs in Long Context"☆35Updated last year
- The official code of "VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning" [NeurIPS25]☆144Updated 3 months ago
- [ICML 2024] Unveiling and Harnessing Hidden Attention Sinks: Enhancing Large Language Models without Training through Attention Calibrati…☆42Updated last year
- G1: Bootstrapping Perception and Reasoning Abilities of Vision-Language Model via Reinforcement Learning☆81Updated 4 months ago
- Official codebase for "GenPRM: Scaling Test-Time Compute of Process Reward Models via Generative Reasoning".☆81Updated 3 months ago
- ☆166Updated 4 months ago
- ☆82Updated last year
- [ACL' 25] The official code repository for PRMBench: A Fine-grained and Challenging Benchmark for Process-Level Reward Models.☆81Updated 7 months ago
- my commonly-used tools☆61Updated 8 months ago
- [ICML'25] Our study systematically investigates massive values in LLMs' attention mechanisms. First, we observe massive values are concen…☆79Updated 3 months ago
- RM-R1: Unleashing the Reasoning Potential of Reward Models☆134Updated 2 months ago
- ☆17Updated 6 months ago
- Github repository for "Bring Reason to Vision: Understanding Perception and Reasoning through Model Merging" (ICML 2025)☆74Updated 3 months ago
- Extrapolating RLVR to General Domains without Verifiers☆160Updated last month
- Code for Math-LLaVA: Bootstrapping Mathematical Reasoning for Multimodal Large Language Models☆89Updated last year
- 🚀 LLaMA-MoE v2: Exploring Sparsity of LLaMA from Perspective of Mixture-of-Experts with Post-Training☆89Updated 9 months ago
- [EMNLP 2024 Findings🔥] Official implementation of ": LOOK-M: Look-Once Optimization in KV Cache for Efficient Multimodal Long-Context In…☆100Updated 10 months ago
- [EMNLP 2024] mDPO: Conditional Preference Optimization for Multimodal Large Language Models.☆81Updated 10 months ago
- [ArXiv] V2PE: Improving Multimodal Long-Context Capability of Vision-Language Models with Variable Visual Position Encoding☆57Updated 9 months ago
- Interleaving Reasoning: Next-Generation Reasoning Systems for AGI☆167Updated last week
- Official implementation of GUI-R1 : A Generalist R1-Style Vision-Language Action Model For GUI Agents☆184Updated 4 months ago
- [2025-TMLR] A Survey on the Honesty of Large Language Models☆59Updated 9 months ago