We propose Reinforcement Learning from Community Feedback (RLCF), a training paradigm that uses large-scale community signals as supervision, and formulate scientific taste learning as a preference modeling and alignment problem.
☆432Sep 22, 2026Updated this week
Alternatives and similar repositories for AI-Can-Learn-Scientific-Taste
Users that are interested in AI-Can-Learn-Scientific-Taste are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- We introduce 'Thinking with Video', a new paradigm leveraging video generation for multimodal reasoning. Our VideoThinkBench shows that S…☆320Aug 23, 2026Updated last month
- ☆146Aug 31, 2026Updated 3 weeks ago
- 启智平台任务管理 CLI：资源查询、任务提交、日志查看和 MCP/agent workflow☆133Updated this week
- An open-weight 11B model series for long-form and real-time video understanding☆731Updated this week
- Create SSH and TCP Proxy to your company container.☆31Jun 10, 2026Updated 3 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.
- A curated list of awesome resources about reward construction for AI agents. This repository covers cutting-edge research, and practical …☆61Sep 1, 2025Updated last year
- DenoiseRL: Bootstrapping Reasoning Models to Recover from Noisy Prefixes☆36Jul 30, 2026Updated last month
- Game-RL: Synthesizing Multimodal Verifiable Game Data to Boost VLMs' General Reasoning☆160Aug 21, 2026Updated last month
- Supercharge your AI agents by versioning, tracking, and merging overlapping skills.☆42Apr 9, 2026Updated 5 months ago
- ☆32Apr 9, 2026Updated 5 months ago
- 启智平台的 Agent 驾驶舱：Skill + CLI，一条命令直达。Agent cockpit for the Inspire ML platform: one command, every operation, straight from chat.☆533Sep 11, 2026Updated last week
- ☆40Jan 1, 2026Updated 8 months ago
- A benchmark for evaluating future-event forecasting from audio and video context in multimodal language models☆29Jan 22, 2026Updated 8 months ago
- [CVPR 2026] IOMM: Fast Pre-training of Unified Multimodal Models without Text-Image Pairs☆26Apr 11, 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.
- A tool for better use of Inspire platform (Beta: Codeberg version is more up-to-date)☆30Apr 2, 2026Updated 5 months ago
- ☆27Jan 29, 2026Updated 7 months ago
- ☆50Dec 21, 2025Updated 9 months ago
- Band-constrained Policy Optimization with probability-aware clipping for LLM reinforcement learning☆50Apr 8, 2026Updated 5 months ago
- daVinci-Agency: Unlocking Long-Horizon Agency Data-Efficiently☆38Feb 4, 2026Updated 7 months ago
- In this work, we investigate the compositionality of large language models (LLMs) in mathematical reasoning. Specifically, we construct a…☆59Mar 15, 2025Updated last year
- FamilyTool benchmark☆14Sep 10, 2025Updated last year
- A foundation model that generates synchronized video and audio in a single model☆1,117Updated this week
- An open-source personal academic homepage template characterized by its user-friendly design and extensive scalability.☆36Oct 6, 2025Updated 11 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.
- A training-free framework that accelerates diffusion language models through dynamic cache eviction and sparse attention☆29Oct 16, 2025Updated 11 months ago
- [CVPR 2026] Official repo for "VideoSSR: Video Self-Supervised Reinforcement Learning"☆48Nov 11, 2025Updated 10 months ago
- An asynchronous file-based handoff protocol for Claude Code and Codex agents sharing one project workspace☆40Jul 4, 2026Updated 2 months ago
- [CVPR 2026] This repository is the official implementation of MVGGT: Multimodal Visual Geometry Grounded Transformer for Multiview 3D Ref…☆134Updated this week
- A 1.6B causal Transformer audio tokenizer with streaming, variable bitrates, and semantic alignment across speech, sound, and music☆258Jun 16, 2026Updated 3 months ago
- ACL 2026 - Muse: Towards Reproducible Long-Form Song Generation with Fine-Grained Style Control☆125Apr 11, 2026Updated 5 months ago
- Codes for the paper "BAPO: Stabilizing Off-Policy Reinforcement Learning for LLMs via Balanced Policy Optimization with Adaptive Clipping…☆96Jan 29, 2026Updated 7 months ago
- An imaginary extension of rotary position embeddings for long-context language models☆33Dec 9, 2025Updated 9 months ago
- ☆141May 12, 2026Updated 4 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- PolicyShiftGuard: Benchmarking and Improving Policy-Adaptive Image Guardrails☆22Jul 8, 2026Updated 2 months ago
- Where Scientific Computing Meets Artificial Intellegence☆54Apr 30, 2026Updated 4 months ago
- [ICML 2026] InnoEval: On Research Idea Evaluation as a Knowledge-Grounded, Multi-Perspective Reasoning Problem☆30Jun 21, 2026Updated 3 months ago
- A post-training framework for diffusion language models with supervised fine-tuning and reinforcement learning☆165Mar 30, 2026Updated 5 months ago
- ICA Lens: compact ICA-based interpretability tools for exploring LLM activations. Code release for the paper.☆45Aug 16, 2026Updated last month
- [Tech Report] Expanded Hyper-Connections☆66Jul 21, 2026Updated 2 months ago
- An open-source model for understanding speech, environmental sounds, and music through captioning, question answering, and reasoning☆670Sep 6, 2026Updated 2 weeks ago