✨HorizonMath: Measuring AI Progress Toward Mathematical Discovery with Automatic Verification

📝 Summary:
HorizonMath is a new benchmark of over 100 unsolved math problems with automatic verification to measure AI discovery progress. It is immune to data contamination because solutions are unknown. GPT 5.4 Pro proposed solutions for two problems that improve on best-known published results.

🔹 Publication Date: Published on Mar 16

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.15617
• PDF: https://arxiv.org/pdf/2603.15617
• Github: https://github.com/ewang26/HorizonMath

==================================

For more data science resources:
✓ https://t.iss.one/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Autonomous Agents Coordinating Distributed Discovery Through Emergent Artifact Exchange

📝 Summary:
We present ScienceClaw + Infinite, a framework for autonomous scientific investigation in which independent agents conduct research without central coordination, and any contributor can deploy new age...

🔹 Publication Date: Published on Mar 15

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.14312
• PDF: https://arxiv.org/pdf/2603.14312
• Project Page: https://lamm.mit.edu/infinite
• Github: https://github.com/lamm-mit/scienceclaw

==================================

For more data science resources:
✓ https://t.iss.one/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research

✨VoXtream2: Full-stream TTS with dynamic speaking rate control

📝 Summary:
Full-stream text-to-speech (TTS) for interactive systems must start speaking with minimal delay while remaining controllable as text arrives incrementally. We present VoXtream2, a zero-shot full-strea...

🔹 Publication Date: Published on Mar 13

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.13518
• PDF: https://arxiv.org/pdf/2603.13518
• Project Page: https://herimor.github.io/voxtream2

🔹 Models citing this paper:
• https://huggingface.co/herimor/voxtream2

✨ Datasets citing this paper:
• https://huggingface.co/datasets/herimor/voxtream2-test
• https://huggingface.co/datasets/herimor/voxtream2-train

✨ Spaces citing this paper:
• https://huggingface.co/spaces/herimor/voxtream2

==================================

For more data science resources:
✓ https://t.iss.one/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research

✨VisionCoach: Reinforcing Grounded Video Reasoning via Visual-Perception Prompting

📝 Summary:
Video reasoning requires models to locate and track question-relevant evidence across frames. While reinforcement learning (RL) with verifiable rewards improves accuracy, it still struggles to achieve...

🔹 Publication Date: Published on Mar 15

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.14659
• PDF: https://arxiv.org/pdf/2603.14659
• Project Page: https://visioncoach.github.io/
• Github: https://visioncoach.github.io/

==================================

For more data science resources:
✓ https://t.iss.one/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research

✨The PokeAgent Challenge: Competitive and Long-Context Learning at Scale

📝 Summary:
The PokeAgent Challenge introduces a large-scale Pokemon benchmark for AI decision-making. It tests strategic reasoning and long-horizon planning, revealing gaps between AI and human performance, making it a key unsolved problem for RL and LLM research.

🔹 Publication Date: Published on Mar 16

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.15563
• PDF: https://arxiv.org/pdf/2603.15563
• Project Page: https://pokeagentchallenge.com/

==================================

For more data science resources:
✓ https://t.iss.one/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Tri-Prompting: Video Diffusion with Unified Control over Scene, Subject, and Motion

📝 Summary:
Tri-Prompting presents a unified framework for video diffusion that enables joint control of scene composition, multi-view subject consistency, and motion, achieving superior performance in identity p...

🔹 Publication Date: Published on Mar 16

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.15614
• PDF: https://arxiv.org/pdf/2603.15614
• Project Page: https://zhouzhenghong-gt.github.io/Tri-Prompting-Page/
• Github: https://zhouzhenghong-gt.github.io/Tri-Prompting-Page/

==================================

For more data science resources:
✓ https://t.iss.one/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Spectrum Matching: a Unified Perspective for Superior Diffusability in Latent Diffusion

📝 Summary:
Variational autoencoders' learnability in latent diffusion is enhanced through spectrum matching techniques that align power-law spectral densities and preserve frequency semantics during encoding and...

🔹 Publication Date: Published on Mar 15

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.14645
• PDF: https://arxiv.org/pdf/2603.14645

==================================

For more data science resources:
✓ https://t.iss.one/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research

✨POLCA: Stochastic Generative Optimization with LLM

📝 Summary:
POLCA is an LLM-based framework for stochastic generative optimization of complex systems. It achieves robust, efficient convergence by managing exploration and stochasticity, outperforming state-of-the-art methods.

🔹 Publication Date: Published on Mar 16

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.14769
• PDF: https://arxiv.org/pdf/2603.14769
• Github: https://github.com/rlx-lab/POLCA

==================================

For more data science resources:
✓ https://t.iss.one/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research

✨AgentProcessBench: Diagnosing Step-Level Process Quality in Tool-Using Agents

📝 Summary:
AgentProcessBench introduces the first benchmark for evaluating step-level effectiveness in tool-augmented AI agents. It uses human-annotated trajectories to diagnose agent failures, revealing challenges in distinguishing errors and the value of process-level signals for improving agent performance.

🔹 Publication Date: Published on Mar 15

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.14465
• PDF: https://arxiv.org/pdf/2603.14465
• Project Page: https://rucbm.github.io/AgentProcessBench-Homepage/
• Github: https://github.com/RUCBM/AgentProcessBench

✨ Datasets citing this paper:
• https://huggingface.co/datasets/LulaCola/AgentProcessBench

==================================

For more data science resources:
✓ https://t.iss.one/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research

✨FlashSampling: Fast and Memory-Efficient Exact Sampling

📝 Summary:
FlashSampling enables efficient categorical sampling by fusing the operation into the language model head matmul, eliminating memory overhead and reducing decoding time by up to 19%. AI-generated summ...

🔹 Publication Date: Published on Mar 16

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.15854
• PDF: https://arxiv.org/pdf/2603.15854
• Project Page: https://github.com/FlashSampling/FlashSampling
• Github: https://github.com/FlashSampling/FlashSampling

==================================

For more data science resources:
✓ https://t.iss.one/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Measuring Primitive Accumulation: An Information-Theoretic Approach to Capitalist Enclosure in PIK2, Indonesia

📝 Summary:
Large-scale land enclosure for speculative mega-development constitutes a non-equilibrium spatial process whose velocity, topology, and irreversibility remain poorly quantified. We study the Pantai In...

🔹 Publication Date: Published on Mar 14

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.13715
• PDF: https://arxiv.org/pdf/2603.13715
• Github: https://github.com/sandyherho/supplPIK2LULC

==================================

For more data science resources:
✓ https://t.iss.one/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Recursive Language Models Meet Uncertainty: The Surprising Effectiveness of Self-Reflective Program Search for Long Context

📝 Summary:
Language models struggle with long-context handling, but a new framework called SRLM improves performance by incorporating uncertainty-aware self-reflection to guide programmatic context interaction, ...

🔹 Publication Date: Published on Mar 7

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.15653
• PDF: https://arxiv.org/pdf/2603.15653

==================================

For more data science resources:
✓ https://t.iss.one/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Online Experiential Learning for Language Models

📝 Summary:
Online Experiential Learning enables continuous improvement of language models through deployment experience by extracting and consolidating experiential knowledge via on-policy distillation. AI-gener...

🔹 Publication Date: Published on Mar 17

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.16856
• PDF: https://arxiv.org/pdf/2603.16856
• Project Page: https://github.com/microsoft/LMOps/tree/main/oel
• Github: https://github.com/microsoft/LMOps/tree/main/oel

==================================

For more data science resources:
✓ https://t.iss.one/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Demystifing Video Reasoning

📝 Summary:
Diffusion-based video models demonstrate reasoning capabilities through denoising steps rather than frame sequences, exhibiting behaviors like working memory, self-correction, and perception-before-ac...

🔹 Publication Date: Published on Mar 17

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.16870
• PDF: https://arxiv.org/pdf/2603.16870
• Project Page: https://www.wruisi.com/demystifying_video_reasoning/

==================================

For more data science resources:
✓ https://t.iss.one/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research

✨WorldCam: Interactive Autoregressive 3D Gaming Worlds with Camera Pose as a Unifying Geometric Representation

📝 Summary:
WorldCam uses camera pose as a unifying geometric representation for interactive 3D gaming worlds. This enables precise action control via a physics-based space and long-term 3D consistency by retrieving observations with global poses.

🔹 Publication Date: Published on Mar 17

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.16871
• PDF: https://arxiv.org/pdf/2603.16871
• Project Page: https://cvlab-kaist.github.io/WorldCam/
• Github: https://github.com/cvlab-kaist/WorldCam

==================================

For more data science resources:
✓ https://t.iss.one/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research

✨SocialOmni: Benchmarking Audio-Visual Social Interactivity in Omni Models

📝 Summary:
SocialOmni presents a benchmark for evaluating social interactivity in omni-modal large language models across speaker identification, interruption timing, and natural interruption generation, reveali...

🔹 Publication Date: Published on Mar 17

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.16859
• PDF: https://arxiv.org/pdf/2603.16859
• Project Page: https://huggingface.co/datasets/alexisty/SocialOmni
• Github: https://github.com/MAC-AutoML/SocialOmni

==================================

For more data science resources:
✓ https://t.iss.one/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Reliable Reasoning in SVG-LLMs via Multi-Task Multi-Reward Reinforcement Learning

📝 Summary:
CTRL-S framework enhances SVG generation through chain-of-thought reasoning and multi-reward optimization, achieving better structural coherence and visual fidelity. AI-generated summary With the rapi...

🔹 Publication Date: Published on Mar 17

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.16189
• PDF: https://arxiv.org/pdf/2603.16189
• Github: https://github.com/hmwang2002/CTRL-S

✨ Datasets citing this paper:
• https://huggingface.co/datasets/InternSVG/SVG-Sophia

==================================

For more data science resources:
✓ https://t.iss.one/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research

✨SegviGen: Repurposing 3D Generative Model for Part Segmentation

📝 Summary:
SegviGen repurposes pretrained 3D generative models for efficient 3D part segmentation using distinctive part colorization, achieving superior performance with minimal labeled data. AI-generated summa...

🔹 Publication Date: Published on Mar 17

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.16869
• PDF: https://arxiv.org/pdf/2603.16869
• Project Page: https://fenghora.github.io/SegviGen-Page/
• Github: https://fenghora.github.io/SegviGen-Page/

==================================

For more data science resources:
✓ https://t.iss.one/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research

✨MiroThinker-1.7 & H1: Towards Heavy-Duty Research Agents via Verification

📝 Summary:
MiroThinker-1.7 and MiroThinker-H1 are research agents that enhance complex reasoning through structured planning, contextual reasoning, and tool interaction, with MiroThinker-H1 incorporating verific...

🔹 Publication Date: Published on Mar 16

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.15726
• PDF: https://arxiv.org/pdf/2603.15726
• Project Page: https://www.miromind.ai/

==================================

For more data science resources:
✓ https://t.iss.one/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research

✨M^3: Dense Matching Meets Multi-View Foundation Models for Monocular Gaussian Splatting SLAM

📝 Summary:
Multi-view foundation model enhanced with matching head and monocular Gaussian splatting SLAM achieves improved pose estimation and scene reconstruction accuracy. AI-generated summary Streaming recons...

🔹 Publication Date: Published on Mar 17

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.16844
• PDF: https://arxiv.org/pdf/2603.16844
• Project Page: https://city-super.github.io/M3/
• Github: https://github.com/InternRobotics/M3

==================================

For more data science resources:
✓ https://t.iss.one/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Learning Human-Object Interaction for 3D Human Pose Estimation from LiDAR Point Clouds

📝 Summary:
Human-Object Interaction Learning framework addresses challenges in 3D human pose estimation from LiDAR point clouds by mitigating spatial ambiguity and class imbalance through contrastive learning an...

🔹 Publication Date: Published on Mar 17

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.16343
• PDF: https://arxiv.org/pdf/2603.16343
• Project Page: https://hoil-release.github.io/

==================================

For more data science resources:
✓ https://t.iss.one/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research