Data science research papers
前往频道在 Telegram
Machine learning and data science research papers Key ML and AI papers with code and GitHub repos. Simple way to follow current research. Join 👉 https://rebrand.ly/bigdatachannels DMCA: @disclosure_bds Contact: @mldatascientist
显示更多3 242
订阅者
+124 小时
+107 天
+1730 天
帖子存档
Scaling Automatic Research Agents via World Models
📅 Publication Date: Aug 29, 2026
📄 Paper: https://arxiv.org/pdf/2608.12564.pdf
🔗 Code: https://github.com/xiyuanyang45/WMRL
💻 Project Page: https://xiyuanyang45.github.io/WMRL/
📝 Description:
World Model RL replaces costly environment execution with a learned world model and applies debiasing and denoising to accelerate post-training of autonomous research agents.
➖➖➖➖➖➖➖➖➖➖➖
📄 More research papers → @data_science_research_papers
Part of @bigdataspecialist community
NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness
📅 Publication Date: Sep 08, 2026
📄 Paper: https://arxiv.org/pdf/2609.08183.pdf
🔗 Code: https://github.com/TokenRhythm/NeoHorse
💻 Project Page: https://huggingface.co/collections/TokenRhythm/neohorse-1
📝 Description:
NeoHorse-1 uses agentic post-training with intelligent routing, structured feedback loops, and curriculum-based distillation to improve model capabilities across agent benchmarks.
➖➖➖➖➖➖➖➖➖➖➖
📄 More research papers → @data_science_research_papers
Part of @bigdataspecialist community
Dr. Claw: An AI Scientist Workspace for Vibe Research
📅 Publication Date: Aug 31, 2026
📄 Paper: https://arxiv.org/pdf/2609.00365.pdf
🔗 Code: https://github.com/OpenLAIR/dr-claw
💻 Project Page: https://github.com/OpenLAIR/dr-claw/
📝 Description:
Command-line coding agents (e.g., Claude Code, Gemini CLI) can already read and write files and sustain long sessions, yet end-to-end research still fragments across chat tools, IDEs, terminals, and writing environments, and the decisions that make it auditable are rarely preserved. We present Dr. C...
➖➖➖➖➖➖➖➖➖➖➖
📄 More research papers → @data_science_research_papers
Part of @bigdataspecialist community
Unlocking Lossless Speedups in LLMs via Discrete Diffusion
📅 Publication Date: Sep 03, 2026
📄 Paper: https://arxiv.org/pdf/2609.04010.pdf
🔗 Code: https://github.com/ifm-ai/uno
💻 Project Page: https://s-sahoo.com/uno/
📝 Description:
Diffusion-augmented autoregressive language models use parallel token sampling via distilled diffusion weights and a specialized sampler to accelerate inference without quality loss or draft models.
➖➖➖➖➖➖➖➖➖➖➖
📄 More research papers → @data_science_research_papers
Part of @bigdataspecialist community
Bilevel Coordinated Reflection: A Game-Theoretic Approach to Multi-Agent LLM Systems
📅 Publication Date: Sep 02, 2026
📄 Paper: https://arxiv.org/pdf/2609.02750.pdf
🔗 Code: https://github.com/YihangChen9/Bilevel-Coordinated-Reflection
📝 Description:
The study formalizes multi-agent LLM coordination via bilevel games and stochastic memory reflection, introducing a grounded evaluation gate and SRMA algorithm with convergence guarantees, validated on SWE-bench.
➖➖➖➖➖➖➖➖➖➖➖
📄 More research papers → @data_science_research_papers
Part of @bigdataspecialist community
📢 Advertising in this channel
You can place an ad via Telega․io. It takes just a few minutes.
Formats and current rates: View details
Show-Harness: Just a VLM Agent Can Play Robots
📅 Publication Date: Sep 09, 2026
📄 Paper: https://arxiv.org/pdf/2609.10522.pdf
🔗 Code: https://github.com/showlab/Show-Harness
💻 Project Page: https://showlab.github.io/Show-Harness/
📝 Description:
Show-Harness links vision-language models to robot control via discrete semantic actions interpreted by embodiment-specific modules, enabling zero-shot and efficient fine-tuned deployment across robots and GUIs.
➖➖➖➖➖➖➖➖➖➖➖
📄 More research papers → @data_science_research_papers
Part of @bigdataspecialist community
Omni Interaction Agent Technical Report
📅 Publication Date: Sep 08, 2026
📄 Paper: https://arxiv.org/pdf/2609.08977.pdf
🔗 Code: https://github.com/Omni-Interaction-Gander/Omni-Interaction-Agent
💻 Project Page: https://omni-interaction-gander.github.io/Omni-Interaction-Agent/
📝 Description:
Gander is an end-to-end framework that integrates continuous multi-modal streaming, real-time full-duplex interaction, and agentic reasoning through a Cerebellum-Brain architecture and a chunk-level token stream design.
➖➖➖➖➖➖➖➖➖➖➖
📄 More research papers → @data_science_research_papers
Part of @bigdataspecialist community
SpatialBlock: Enhancing Spatial Intelligence in LVLMs via Synthetic Block-Stacking Problem
📅 Publication Date: Sep 07, 2026
📄 Paper: https://arxiv.org/pdf/2609.07064.pdf
🔗 Code: https://github.com/rsoohyun/SpatialBlock
📝 Description:
Large vision-language models trained on synthetic block-manipulation tasks improve 3D spatial reasoning and generalize to real-world visual tasks.
➖➖➖➖➖➖➖➖➖➖➖
📄 More research papers → @data_science_research_papers
Part of @bigdataspecialist community
Programmable World Model
📅 Publication Date: Sep 09, 2026
📄 Paper: https://arxiv.org/pdf/2609.10540.pdf
🔗 Code: https://github.com/AlayaLab/pwm
💻 Project Page: https://alaya-lab.github.io/pwm/
📝 Description:
A programmable world model separates explicit state evolution from video generation using executable rules and 3D bounding boxes to maintain persistent, controllable environments.
➖➖➖➖➖➖➖➖➖➖➖
📄 More research papers → @data_science_research_papers
Part of @bigdataspecialist community
Repo-To-Skill: Distilling GitHub Repositories Into AI4AI Skills
📅 Publication Date: Sep 02, 2026
📄 Paper: https://arxiv.org/pdf/2609.02749.pdf
🔗 Code: https://github.com/VectorSpaceLab/AREX-Skill
📝 Description:
DisCo is a research agent that distills operational knowledge into reusable skills, significantly improving autonomous ML research performance across benchmarks.
➖➖➖➖➖➖➖➖➖➖➖
📄 More research papers → @data_science_research_papers
Part of @bigdataspecialist community
Compile by Training: Turning Natural-Language Specifications into Local Neural Functions
📅 Publication Date: Sep 03, 2026
📄 Paper: https://arxiv.org/pdf/2609.04199.pdf
🔗 Code: https://github.com/programasweights/compile-by-training
💻 Project Page: https://programasweights.com/playground?compiler=paw-ft-bs48
📝 Description:
Compile by training converts natural-language specifications into reusable neural functions by distilling teacher-generated examples into small adapters, enabling efficient deployment without remote model dependencies.
➖➖➖➖➖➖➖➖➖➖➖
📄 More research papers → @data_science_research_papers
Part of @bigdataspecialist community
SolarWM: Open Data and Scalable Training for Long-Horizon Video World Models
📅 Publication Date: Sep 02, 2026
📄 Paper: https://arxiv.org/pdf/2609.02886.pdf
🔗 Code: https://github.com/Junchao-cs/SolarWM
💻 Project Page: https://junchao-cs.github.io/SolarWM-Web/
📝 Description:
SolarWM provides an open framework and unified training recipe for building interactive video world models across diverse data sources and generator backbones, enabling long-horizon real-time rollouts.
➖➖➖➖➖➖➖➖➖➖➖
📄 More research papers → @data_science_research_papers
Part of @bigdataspecialist community
RoboTok: An Internet-Scale Data Engine for Human Demonstration Retrieval and Dexterous Manipulation Learning
📅 Publication Date: Sep 02, 2026
📄 Paper: https://arxiv.org/pdf/2609.03199.pdf
🔗 Code: https://github.com/Rice-RobotPI-Lab/RoboTok-Code
💻 Project Page: https://rice-robotpi-lab.github.io/RoboTok/
📝 Description:
RoboTok retrieves relevant human manipulation videos from the web using a latent motion space derived from 3D hand trajectories to improve robot policy training.
➖➖➖➖➖➖➖➖➖➖➖
📄 More research papers → @data_science_research_papers
Part of @bigdataspecialist community
EarlyEval: Cheaper Agent Evaluation via Early Outcome Prediction
📅 Publication Date: Sep 02, 2026
📄 Paper: https://arxiv.org/pdf/2609.02783.pdf
🔗 Code: https://github.com/inphotoo/earlyeval
📝 Description:
EarlyEval predicts agent outcomes from intermediate behavior to reduce evaluation cost by halting runs early with minimal accuracy loss.
➖➖➖➖➖➖➖➖➖➖➖
📄 More research papers → @data_science_research_papers
Part of @bigdataspecialist community
RRSI: Regularized Recursive Self-Improvement of Agent Harnesses
📅 Publication Date: Sep 21, 2026
📄 Paper: https://arxiv.org/pdf/2609.24972.pdf
🔗 Code: https://github.com/google-research/rrsi
💻 Project Page: https://regularized-rsi.com/
📝 Description:
An LLM agent's capability is largely magnified by its harness, namely the prompts, control flow, tooling, memory, and context management surrounding the frozen backbone model.
➖➖➖➖➖➖➖➖➖➖➖
📄 More research papers → @data_science_research_papers
Part of @bigdataspecialist community
LatentPress: Context Compression Beyond Text and Vision
📅 Publication Date: Sep 01, 2026
📄 Paper: https://arxiv.org/pdf/2609.01507.pdf
🔗 Code: https://github.com/HJSang/LatentPress
💻 Project Page: https://github.com/HJSang/LatentPress
📝 Description:
LatentPress compresses conversational and document context into continuous memory tokens read directly by a frozen decoder, achieving high compression with faster inference and improved accuracy over text or OCR methods.
➖➖➖➖➖➖➖➖➖➖➖
📄 More research papers → @data_science_research_papers
Part of @bigdataspecialist community
LoopArena: Benchmarking Models as Runtime Controllers for Loop Engineering
📅 Publication Date: Aug 28, 2026
📄 Paper: https://arxiv.org/pdf/2608.28281.pdf
🔗 Code: https://github.com/AMAP-ML/LoopArena
💻 Project Page: https://amap-ml.github.io/LoopArena/
📝 Description:
LoopArena benchmarks how well a controller model guides a separate coding agent through long tasks, revealing low strict success rates and significant cost reductions.
➖➖➖➖➖➖➖➖➖➖➖
📄 More research papers → @data_science_research_papers
Part of @bigdataspecialist community
UrbanGround: From Local Perception to Spatial Agency in a Real-Scale City
📅 Publication Date: Aug 27, 2026
📄 Paper: https://arxiv.org/pdf/2608.27456.pdf
🔗 Code: https://github.com/UrbanGround/UrbanGround
💻 Project Page: https://urbanground.github.io
📝 Description:
UrbanGround evaluates whether multimodal language model agents can sustain reliable navigation and spatial reasoning in a realistic 3D city replica, revealing that local perceptual skills fail to compose into extended goal-directed behavior.
➖➖➖➖➖➖➖➖➖➖➖
📄 More research papers → @data_science_research_papers
Part of @bigdataspecialist community
PAWBench: How Far Are We from Probabilistically Aligned World Modeling?
📅 Publication Date: Aug 27, 2026
📄 Paper: https://arxiv.org/pdf/2608.27345.pdf
🔗 Code: https://github.com/Andrew0613/PAWBench
💻 Project Page: https://pawbench.github.io/
📝 Description:
The study formalizes probabilistic alignment for world models, introduces PAWBench and PAWEval to evaluate video generators as stochastic samplers, and finds current models fail to match reference behavior distributions.
➖➖➖➖➖➖➖➖➖➖➖
📄 More research papers → @data_science_research_papers
Part of @bigdataspecialist community
