xinghaow99 / BitStackLinks
[ICLR 2025] BitStack: Any-Size Compression of Large Language Models in Variable Memory Environments
☆39Updated 11 months ago
Alternatives and similar repositories for BitStack
Users that are interested in BitStack are comparing it to the libraries listed below
Sorting:
- [Neurips 2025] R-KV: Redundancy-aware KV Cache Compression for Reasoning Models☆1,174Updated 3 months ago
- Official code implementation of Context Cascade Compression: Exploring the Upper Limits of Text Compression☆284Updated last week
- UR2: Unify RAG and Reasoning through Reinforcement Learning☆126Updated 2 months ago
- [ICML 2025] "SepLLM: Accelerate Large Language Models by Compressing One Segment into One Separator"☆561Updated 6 months ago
- [NeurIPS 2025🔥]Main source code of SRPO framework.☆186Updated 2 months ago
- [AAAI 2026 Oral] Official repository for InfiGUI-G1. We introduce Adaptive Exploration Policy Optimization (AEPO) to overcome semantic al…☆129Updated 2 months ago
- ☆280Updated last month
- [NeurIPS2024] Twin-Merging: Dynamic Integration of Modular Expertise in Model Merging☆140Updated 10 months ago
- [Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics]: VisuoThink: Empowering LVLM Reasoning with Mul…☆101Updated 6 months ago
- A simple, unified multimodal models training engine. Lean, flexible, and built for hacking at scale.☆706Updated 2 weeks ago
- [AAAI'26, Oral] Code for "Teaching Large Language Models to Maintain Contextual Faithfulness via Synthetic Tasks and Reinforcement Learni…☆43Updated 6 months ago
- Official repository of DARE: dLLM Alignment and Reinforcement Executor☆159Updated this week
- A toolkit enhances PyTorch with specialized functions for low-bit quantized neural networks.☆196Updated last year
- On Predictability of Reinforcement Learning Dynamics for Large Language Models (ICLR 2026)☆54Updated last week
- [NeurIPS'25] KVCOMM: Online Cross-context KV-cache Communication for Efficient LLM-based Multi-agent Systems☆127Updated 3 months ago
- ScaleCUA is the open-sourced computer use agents that can operate on cross-platform environments (Windows, macOS, Ubuntu, Android).☆1,067Updated last month
- Repo-level benchmark for real-world Code Agents: from repo understanding → env setup → incremental dev/bug-fixing → task delivery, with c…☆245Updated 4 months ago
- ☆257Updated last month
- An adaptive sampling framework for Reinforce-style LLM post training.☆88Updated 2 months ago
- R1-like Computer-use Agent☆88Updated 10 months ago
- EvaLearn is a pioneering benchmark designed to evaluate large language models (LLMs) on their learning capability and efficiency in chall…☆430Updated 2 weeks ago
- Marco Search Agent for Realistic and Challenging Agentic Search☆240Updated 3 months ago
- [AAAI 2026] GUI-G²: Gaussian Reward Modeling for GUI Grounding☆299Updated this week
- **Deep Video Discovery (DVD)** is a deep-research style question answering agent designed for understanding extra-long videos.☆346Updated 3 months ago
- Beyond log-likelihood: exploring alternative objectives for supervised fine-tuning of language model post-training☆55Updated 4 months ago
- [TMLR'25] The Curse of CoT: On the Limitations of Chain-of-Thought in In-Context Learning☆53Updated 9 months ago
- [NIPS'25 Spotlight] Mulberry, an o1-like Reasoning and Reflection MLLM Implemented via Collective MCTS☆1,238Updated 3 weeks ago
- [ICML2025] Make LoRA Great Again: Boosting LoRA with Adaptive Singular Values and Mixture-of-Experts Optimization Alignment☆139Updated 2 months ago
- ☆104Updated 8 months ago
- MTLA: Multi-head Temporal Latent Attention☆760Updated 4 months ago