The official repository of the paper Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models
☆21Sep 14, 2026Updated last month
Alternatives and similar repositories for PUMA
Users that are interested in PUMA are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- [NeurIPS 2025] A*-Thought: Efficient Reasoning via Bidirectional Compression for Low-Resource Settings☆31Nov 3, 2026Updated last week
- ☆29May 17, 2026Updated 5 months ago
- ☆12Mar 3, 2025Updated last year
- ☆10Sep 18, 2024Updated 2 years ago
- [ICLR 2026] "Test-Time Scaling in Diffusion LLMs via Hidden Semi-Autoregressive Experts"☆15Feb 10, 2026Updated 9 months ago
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- Repository for paper: Contexts are Never Long Enough: Structured Reasoning for Scalable Question Answering over Long Document Sets☆31Apr 27, 2026Updated 6 months ago
- Official implementation of Decoupled Reasoning with Implicit Fact Tokens (DRIFT): A Dual-Model Framework for Efficient Long-Context Infer…☆12May 13, 2026Updated 5 months ago
- Advanced Programming - HW7☆12Jun 9, 2022Updated 4 years ago
- [EMNLP 2025 - Oral] MovieCORE: COgnitive REasoning in Movies☆12Sep 2, 2025Updated last year
- ☆16Apr 15, 2024Updated 2 years ago
- ☆12Apr 13, 2026Updated 6 months ago
- SystemC-Based Simulator for Early Exploration of Networks On-Chip☆13Oct 25, 2019Updated 7 years ago
- ☆11Mar 27, 2025Updated last year
- Reverse Engineering of the Mythos Architecture — What I Think☆25May 15, 2026Updated 5 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.
- MICRO 2023 Evaluation Artifact for TeAAL☆13Oct 26, 2023Updated 3 years ago
- ☆13Apr 6, 2026Updated 7 months ago
- ☆23Jan 18, 2021Updated 5 years ago
- This is the official implementation of "DiffVsgg: Diffusion-Driven Online Video Scene Graph Generation" (Accepted at CVPR 2025).☆13Mar 5, 2025Updated last year
- Semantic Self-adaptation: Enhancing Generalization with a Single Sample (TMLR 2023)☆18Jul 21, 2023Updated 3 years ago
- 010Editor-Crack version:13.0.1☆10Mar 18, 2024Updated 2 years ago
- ☆14Apr 28, 2024Updated 2 years ago
- LoCaLUT_AE☆13Dec 8, 2025Updated 11 months ago
- Structure-aware RAG for financial document QA - 82% on FinanceBench. LLM navigates section headings instead of searching embeddings.☆13Apr 15, 2026Updated 6 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.
- Source code for XPGraph-MICRO22☆11Apr 10, 2023Updated 3 years ago
- [ICML 2026] NITP: Next Implicit Token Prediction for LLM Pre-training☆36May 26, 2026Updated 5 months ago
- ICCV2023 paper on Tubelet-Contrastive Self-Supervision for Video-Efficient Generalization☆11Oct 12, 2023Updated 3 years ago
- ☆13Oct 25, 2024Updated 2 years ago
- Advanced Programming - HW4☆17Apr 23, 2022Updated 4 years ago
- Identify which embedding model produced a vector using digit-level tokenization and a tiny transformer☆23Mar 7, 2026Updated 8 months ago
- Probing VLM vs VGM for spatial understanding.☆15Oct 18, 2026Updated 3 weeks ago
- Learnable Semi-structured Sparsity for Vision Transformers and Diffusion Transformers☆16Feb 7, 2025Updated last year
- Guess What Moves: Unsupervised Video and Image Segmentation by Anticipating Motion☆26Mar 16, 2023Updated 3 years ago
- End-to-end encrypted cloud storage - Proton Drive • AdSpecial offer: 40% Off Yearly / 80% Off First Month. Protect your most important files, photos, and documents from prying eyes.
- ☆16Dec 19, 2023Updated 2 years ago
- [CVPR 2025] Accelerating Diffusion Transformer via Increment-Calibrated with Channel-Aware Singular Value Decomposition☆14May 14, 2025Updated last year
- ☆18Dec 25, 2023Updated 2 years ago
- Official implementation of "Don't Ask the LLM: Visual Token Pruning with Spectral Structure and Semantic Relevance" (WACV 2027)☆23Updated this week
- ☆14May 29, 2026Updated 5 months ago
- [CVPR 2024] Official repository of ST_GT☆10Sep 15, 2024Updated 2 years ago
- mul-BERT, the official score on the SemEval 2010 Task 8 dataset is up to 90.72 (Macro-F1).☆16Jan 11, 2021Updated 5 years ago
Are these results useful?