The implementation of Teachability-Aware On-Policy Distillation (TA-OPD), the method introduced in Not All Disagreement Is Learnable: Token Teachability in On-Policy Distillation.
☆22May 25, 2026Updated 5 months ago
Alternatives and similar repositories for TA-OPD
Users that are interested in TA-OPD are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆22Jul 31, 2026Updated 3 months ago
- ☆29Sep 7, 2026Updated 2 months ago
- Codebase for "How Alignment Shrinks the Generative Horizon"☆13Aug 8, 2026Updated 3 months ago
- Code for Paper 'DelTA: Discriminative Token Credit Assignment for Reinforcement Learning from Verifiable Rewards'☆18May 21, 2026Updated 5 months ago
- ☆23Jun 3, 2026Updated 5 months 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.
- Repo for "STAR: Spectral Truncation and Rescale for Model Merging" [NAACL 2025]☆11Oct 22, 2026Updated 3 weeks ago
- ☆63Jul 29, 2026Updated 3 months ago
- An extension of veRL for post-training LLM reasoners with on-policy self-distillation and self-distilled RLVR + the official codebase for…☆80Oct 13, 2026Updated last month
- Implementation of "Does On-Policy Distillation Really Distill? From Noisy Teacher to Self-Improvement"☆57Sep 29, 2026Updated last month
- [ICLR 2025] Official implementation of "Mitigating Parameter Interference in Model Merging via Sharpness-Aware Fine-Tuning"☆11Apr 21, 2025Updated last year
- Official implementation for NeurIPS 2025 paper "SemCoT: Accelerating Chain-of-Thought Reasoning through Semantically-Aligned Implicit Tok…☆23Nov 7, 2025Updated last year
- Uni-OPD: Unifying On-Policy Distillation with a Dual-Perspective Recipe☆57Jun 10, 2026Updated 5 months ago
- Embedding-based skill retrieval plugin for Claude Code. Top-K skills from a 16,783-skill corpus injected as additionalContext on every pr…☆14May 12, 2026Updated 6 months ago
- [ICML 2024] Code release for "On the Emergence of Cross-Task Linearity in Pretraining-Finetuning Paradigm"☆11Feb 20, 2025Updated 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.
- Continual Model Merging without Data: Dual Projections for Balancing Stability and Plasticity. NeurIPS, 2025.☆13Oct 12, 2025Updated last year
- [ACL 2026] Dissecting Failure Dynamics in Large Language Model Reasoning☆19Apr 17, 2026Updated 6 months ago
- [ICLR 2026] Skill-Targeted Adaptive Training☆30Mar 12, 2026Updated 8 months ago
- [ICML 2023] "Robust Weight Signatures: Gaining Robustness as Easy as Patching Weights?" by Ruisi Cai, Zhenyu Zhang, Zhangyang Wang☆16May 4, 2023Updated 3 years ago
- ☆88Aug 17, 2026Updated 2 months ago
- [ACL '26] UNCODE (a.k.a. PC-Sampler): training-free decoding calibration for masked diffusion LLMs. Code for "Empirical Analysis of Decod…☆46Oct 24, 2026Updated 2 weeks ago
- ☆44May 28, 2026Updated 5 months ago
- On Policy Distillation Build on top of Verl☆106Sep 3, 2026Updated 2 months ago
- Codes and data for KDD 2024 Research Track paper "ProCom: A Few-shot Targeted Community Detection Algorithm"☆11Aug 15, 2024Updated 2 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.
- Official implement on 'What and When to Distill: Selective Hindsight Distillation for Multi-Turn Agents'☆26Jun 29, 2026Updated 4 months ago
- The implementation of ACL 2026 paper "Rethinking entropy interventions in rlvr: An entropy change perspective"☆29Oct 15, 2026Updated 3 weeks ago
- ☆34Oct 13, 2025Updated last year
- Official code for FutureBridge-OPD☆26Sep 20, 2026Updated last month
- Official implementation of OPD-Aha for fine-grained visual perception and multimodal reasoning☆15Sep 16, 2026Updated last month
- Modality-Adaptive Decoding (MAD) is a training-free decoding method for MLLMs that adaptively weights modality-specific branches via self…☆16Jun 22, 2026Updated 4 months ago
- SyMerge: From Non-Interference to Synergistic Merging via Single-Layer Adaptation☆12Jul 6, 2026Updated 4 months ago
- ☆12Jan 13, 2026Updated 10 months ago
- An evaluation framework for Text to SQL tasks☆14Oct 12, 2026Updated last month
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- ☆11May 17, 2026Updated 5 months ago
- RA-Touch: Retrieval-Augmented Touch Understanding with Enriched Visual Data (ACM MM '25)☆15Sep 12, 2025Updated last year
- Source code of paper "RLCSD: Reinforcement Learning with Contrastive On-Policy Self-Distillation"☆116Sep 14, 2026Updated 2 months ago
- ☆13Oct 9, 2025Updated last year
- ☆27Jan 29, 2026Updated 9 months ago
- Instant Graph Neural Networks for Dynamic Graphs☆11Dec 28, 2022Updated 3 years ago
- [ICML 2026] Restoring Exploration after Post-Training: Latent Exploration Decoding for Large Reasoning Models☆13May 8, 2026Updated 6 months ago
Are these results useful?