Official implementation of BandPO: Bridging Trust Regions and Ratio Clipping via Probability-Aware Bounds for LLM Reinforcement Learning. BandPO replaces canonical clipping (PPO/GRPO) with dynamic bounds to resolve exploration bottlenecks and prevent entropy collapse.
☆49Apr 8, 2026Updated 2 months ago
Alternatives and similar repositories for BandPO
Users that are interested in BandPO are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Official code for paper "GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable R…☆64Mar 29, 2026Updated 2 months ago
- Redundancy Undermines the Trustworthiness of Self-Interpretable GNNs, International Conference on Machine Learning (ICML), 2025☆15Jun 23, 2025Updated 11 months ago
- Code release for "TinySpeech: Attention Condensers for Deep Speech Recognition Neural Networks on Edge Devices"☆23Jun 7, 2025Updated last year
- [NeurIPS 2025] Better Tokens for Better 3D: Advancing Vision-Language Modeling in 3D Medical Imaging☆40Nov 4, 2025Updated 7 months ago
- 3DSlicer plugin for inpainting lung nodules in 3D chest CT data.☆11Dec 2, 2024Updated last year
- 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.
- ☆14Nov 26, 2025Updated 6 months ago
- This is the official code for the paper "Reconstruct before Query: Continual Missing Modality Learning with Decomposed Prompt Collaborati…☆12Aug 13, 2024Updated last year
- UI-Voyager: A Self-Evolving GUI Agent Learning via Failed Experience☆72Apr 3, 2026Updated 2 months ago
- An Adaptive Multi-Agent Framework for Dynamic Fact-Checking Evaluation of Large Language Models☆17Feb 27, 2025Updated last year
- [EMNLP'2023 Findings] MoqaGPT, for zero-shot multimodal question answering with LLMs☆13Dec 28, 2024Updated last year
- [ACL 2025] "CoT-UQ: Improving Response-wise Uncertainty Quantification in LLMs with Chain-of-Thought"☆17Apr 3, 2025Updated last year
- ☆12Aug 25, 2023Updated 2 years ago
- An implementation of Jasper, QuartzNet, Citrinet and pipeline for training CTC-based ASR models☆12Nov 13, 2021Updated 4 years ago
- ✂️ Trim sequencing adapters from NGS data automatically☆14Sep 5, 2025Updated 9 months ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- [WWW 2025] Following Clues, Approaching the Truth: Explainable Micro-Video Rumor Detection via Chain-of-Thought Reasoning☆23Apr 17, 2026Updated last month
- ☆45Jun 25, 2025Updated 11 months ago
- IMG: Calibrating Diffusion Models via Implicit Multimodal Guidance, ICCV 2025☆30Oct 1, 2025Updated 8 months ago
- ☆12Feb 24, 2023Updated 3 years ago
- ☆19Oct 28, 2025Updated 7 months ago
- ArtSpeech: Adaptive Text-to-Speech Synthesis with Articulatory Representations☆21Sep 21, 2025Updated 8 months ago
- ☆25Nov 25, 2025Updated 6 months ago
- [ACL 2026 Main] Open-Ended Speaking Style Modeling via Fine-Grained and Multi-Granular Contrastive Language-Speech Pre-training☆83Apr 6, 2026Updated 2 months ago
- kimi逆向api☆21Jul 14, 2024Updated last year
- 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.
- [WWW] Kardia-R1: Unleashing LLMs to Reason toward Understanding and Empathy for Emotional Support via Rubric-as-Judge Reinforcement Learn…☆59Mar 2, 2026Updated 3 months ago
- ClusterKV: Manipulating LLM KV Cache in Semantic Space for Recallable Compression (DAC'25)☆29Feb 26, 2026Updated 3 months ago
- 飞书Clawdbot配置指南☆42Jan 30, 2026Updated 4 months ago
- The PyTorch implementation for "DEAL: Disentangle and Localize Concept-level Explanations for VLMs" (ECCV 2024 Strong Double Blind)☆20Mar 9, 2026Updated 3 months ago
- [ICML 2026 Oral] Minimalist RL for Diffusion LLMs. 89.1% on GSM8K.☆145May 26, 2026Updated 2 weeks ago
- RLLaVA is a user-friendly framework for multi-modal RL research and optimized for resource-constrained teams.☆58Mar 18, 2026Updated 2 months ago
- [ICLR 2025] COME: Test-time Adaption by Conservatively Minimizing Entropy☆23Mar 5, 2025Updated last year
- [AAAI 2026] Official repository of Circulant Attention☆58Jan 12, 2026Updated 4 months ago
- CTC decoder with hotwords for ASR.☆36Apr 13, 2025Updated last year
- 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.
- MMRA: Predicting Micro-video Popularity via Multi-modal Retrieval Augmentation, ACM SIGIR Conference on Research and Development in Infor…☆23Feb 7, 2026Updated 4 months ago
- A flexible & scalable MLLM-based AIGC detection pipeline☆37Oct 27, 2025Updated 7 months ago
- Synth-Empathy: Towards High-Quality Synthetic Empathy Data☆18Feb 28, 2025Updated last year
- ACL 2023: Evaluating Open-Domain Question Answering in the Era of Large Language Models☆47Jan 12, 2024Updated 2 years ago
- AAAI '25. Retrieval-Augmented Multimodal Social Media Popularity Prediction☆23Apr 27, 2026Updated last month
- [ASRU 2025] Omni-R1: Do You Really Need Audio to Fine-Tune Your Audio LLM?☆47Nov 21, 2025Updated 6 months ago
- Incremental Disentanglement for Environment-Aware Zero-Shot Text-to-Speech Synthesis☆27Mar 21, 2025Updated last year