[NeurIPS 2025] Mind the Gap: Bridging Thought Leap for Improved CoT Tuning https://arxiv.org/abs/2505.14684
☆45Oct 20, 2025Updated 4 months ago
Alternatives and similar repositories for Mind-the-Gap
Users that are interested in Mind-the-Gap are comparing it to the libraries listed below
Sorting:
- [NeurIPS 2025] Let LRMs Break Free from Overthinking via Self-Braking Tuning. https://arxiv.org/abs/2505.14604☆55Nov 4, 2025Updated 4 months ago
- Benchmarking agent reasoning capabilities in physical interactions, tool usage, and multi-agent coordination.☆42Aug 10, 2025Updated 6 months ago
- ☆32Aug 11, 2025Updated 6 months ago
- ViewSpatial-Bench:Evaluating Multi-perspective Spatial Localization in Vision-Language Models☆70Jan 8, 2026Updated 2 months ago
- GSM8K-V: Can Vision Language Models Solve Grade School Math Word Problems in Visual Contexts☆39Sep 30, 2025Updated 5 months ago
- [ICLR 2026] InftyThink: Breaking the Length Limits of Long-Context Reasoning in Large Language Models☆47Feb 12, 2026Updated 3 weeks ago
- This repository is the official implementation of TimeHC-RL (Distilabel (Data Generation) + TRL (SFT) + VeRL (GRPO)).☆48Jun 4, 2025Updated 9 months ago
- ☆25Aug 19, 2025Updated 6 months ago
- [AAAI 2026] Test-Time Reinforcement Learning for GUI Grounding via Region Consistency https://arxiv.org/abs/2508.05615☆61Nov 8, 2025Updated 4 months ago
- A Unified Framework for High-Performance and Extensible LLM Steering☆187Updated this week
- [ACM MM 2025] SVGenius: Benchmarking LLMs in SVG Understanding, Editing and Generation. https://arxiv.org/abs/2506.03139☆75Nov 10, 2025Updated 3 months ago
- A curated collection of resources, tools, and frameworks for developing GUI Agents.☆311Mar 2, 2026Updated last week
- Accepted at IJCAI-2022☆11Sep 3, 2022Updated 3 years ago
- Official implementation of Self-Taught Agentic Long Context Understanding (ACL 2025).☆12Sep 22, 2025Updated 5 months ago
- ☆20May 14, 2025Updated 9 months ago
- 🌟Official code of our AAAI26 paper 🔍WebFilter☆38Nov 9, 2025Updated 4 months ago
- Targeted Data Generation with Large Language Models☆19Jun 25, 2024Updated last year
- ☆59Jul 21, 2025Updated 7 months ago
- (ACL 2025 Main) Distilling RAG for SLMs from LLMs to Transfer Knowledge and Mitigate Hallucination via Evidence and Graph-based Distillat…☆34Aug 23, 2025Updated 6 months ago
- Documentation at☆14Mar 27, 2025Updated 11 months ago
- 一个支持跨模态大语言模型的webui. A chatbot webui that supports various multi-modal large language models☆11May 8, 2023Updated 2 years ago
- [AAAI 2025] Neural-Symbolic Collaborative Distillation: Advancing Small Language Models for Complex Reasoning Tasks☆11Jun 19, 2025Updated 8 months ago
- An Advanced Basic Math Reasoning and Overthinking Evaluation Framework for LLMs☆12Jul 8, 2025Updated 8 months ago
- ☆12Oct 30, 2022Updated 3 years ago
- TOD-Flow: Modeling the Structure of Task-Oriented Dialogues☆13Feb 7, 2024Updated 2 years ago
- ☆10Sep 29, 2024Updated last year
- Source code for SWIFT, an efficient reward model.☆18Jan 13, 2026Updated last month
- Easy and Efficient dLLM Fine-Tuning☆229Mar 2, 2026Updated last week
- Codes for "Learning bounds for risk-sensitive learning," NeurIPS 2020 (or see arXiv 2006.08138)☆11Oct 15, 2020Updated 5 years ago
- A tool for extracting plain text and internal Wikipedia links from Wikipedia dumps☆11Apr 18, 2019Updated 6 years ago
- The code for ”T-GRAG: A Dynamic GraphRAG Framework for Resolving Temporal Conflicts and Redundancy in Knowledge Retrieval“☆21Jul 30, 2025Updated 7 months ago
- [EMNLP 2025 Findings] Familiarity-aware Evidence Compression for Retrieval Augmented Generation☆14Aug 20, 2025Updated 6 months ago
- Simulation code and data of the paper - cold start to improve market thickness☆12Jan 30, 2026Updated last month
- An example for deploying Tensorflow 2 models with Docker and Fast API☆10Sep 30, 2022Updated 3 years ago
- Repository for SPECTRA: Sparse Structured Text Rationalization, accepted at EMNLP 2021 main conference.☆10Feb 14, 2024Updated 2 years ago
- This repository includes the data and scripts utilized in the study titled "Improving LLM-based Verilog Code Generation with Data Augment…☆13Mar 24, 2025Updated 11 months ago
- The first large scale formally verified reasoning dataset for Verilog☆20May 16, 2025Updated 9 months ago
- ☆21Jul 12, 2025Updated 7 months ago
- This repository provides the code for applying Contrastive Learning Penalty Loss (CLPL) and Mixture of Experts (MoE) to the BGE-M3 text e…☆11Dec 27, 2024Updated last year