✨Anatomy of a Lie: A Multi-Stage Diagnostic Framework for Tracing Hallucinations in Vision-Language Models

📝 Summary:
Vision-Language Models (VLMs) frequently "hallucinate" - generate plausible yet factually incorrect statements - posing a critical barrier to their trustworthy deployment. In this work, we propose a n...

🔹 Publication Date: Published on Mar 16

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.15557
• PDF: https://arxiv.org/pdf/2603.15557
• Github: https://github.com/Lexiang-Xiong/CAD

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

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

#VLM #AIHallucinations #TrustworthyAI #ExplainableAI #AIResearch

✨EnterpriseOps-Gym: Environments and Evaluations for Stateful Agentic Planning and Tool Use in Enterprise Settings

📝 Summary:
EnterpriseOps-Gym is a new benchmark for evaluating LLM agents in realistic enterprise settings, featuring a complex sandbox and curated tasks. It reveals current models struggle with strategic planning and task refusal, achieving low success rates, indicating they are not ready for autonomous de...

🔹 Publication Date: Published on Mar 13

🔹 Paper Links:
• arXiv Page: https://arxiv.org/pdf/2603.13594
• PDF: https://arxiv.org/pdf/2603.13594
• Project Page: https://enterpriseops-gym.github.io/
• Github: https://enterpriseops-gym.github.io

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

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

#LLMAgents #EnterpriseAI #AIResearch #Benchmarking #ToolUse

✨When Does Sparsity Mitigate the Curse of Depth in LLMs

📝 Summary:
Recent work has demonstrated the curse of depth in large language models (LLMs), where later layers contribute less to learning and representation than earlier layers. Such under-utilization is linked...

🔹 Publication Date: Published on Mar 16

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.15389
• PDF: https://arxiv.org/pdf/2603.15389
• Project Page: https://pumpkin-co.github.io/SparsityAndCoD/
• Github: https://github.com/pUmpKin-Co/SparsityAndCoD

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨RS-WorldModel: a Unified Model for Remote Sensing Understanding and Future Sense Forecasting

📝 Summary:
Remote sensing world models aim to both explain observed changes and forecast plausible futures, two tasks that share spatiotemporal priors. Existing methods, however, typically address them separatel...

🔹 Publication Date: Published on Mar 16

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.14941
• PDF: https://arxiv.org/pdf/2603.14941

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨sebis at ArchEHR-QA 2026: How Much Can You Do Locally? Evaluating Grounded EHR QA on a Single Notebook

📝 Summary:
Clinical question answering over electronic health records (EHRs) can help clinicians and patients access relevant medical information more efficiently. However, many recent approaches rely on large c...

🔹 Publication Date: Published on Mar 14

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.13962
• PDF: https://arxiv.org/pdf/2603.13962
• Github: https://github.com/ibrahimey/ArchEHR-QA-2026

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Make it SING: Analyzing Semantic Invariants in Classifiers

📝 Summary:
All classifiers, including state-of-the-art vision models, possess invariants, partially rooted in the geometry of their linear mappings. These invariants, which reside in the null-space of the classi...

🔹 Publication Date: Published on Mar 15

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.14610
• PDF: https://arxiv.org/pdf/2603.14610
• Project Page: https://harel314.github.io/SING-analyzing-semantic-invariants-classifiers/
• Github: https://github.com/harel314/SING-analyzing-semantic-invariants-classifiers

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Towards Generalizable Robotic Manipulation in Dynamic Environments

📝 Summary:
Vision-Language-Action (VLA) models excel in static manipulation but struggle in dynamic environments with moving targets. This performance gap primarily stems from a scarcity of dynamic manipulation ...

🔹 Publication Date: Published on Mar 16

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.15620
• PDF: https://arxiv.org/pdf/2603.15620
• Project Page: https://h-embodvis.github.io/DOMINO/
• Github: https://github.com/H-EmbodVis/DOMINO

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨OxyGen: Unified KV Cache Management for Vision-Language-Action Models under Multi-Task Parallelism

📝 Summary:
OxyGen unifies KV cache management for multi-task Vision-Language-Action models, addressing inefficiency from isolated caches. By treating KV cache as a shared resource, it enables cross-task sharing and continuous batching. This achieves up to 3.7 times speedup, providing high language throughpu...

🔹 Publication Date: Published on Mar 15

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.14371
• PDF: https://arxiv.org/pdf/2603.14371
• Github: https://github.com/air-embodied-brain/OxyGen

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Garments2Look: A Multi-Reference Dataset for High-Fidelity Outfit-Level Virtual Try-On with Clothing and Accessories

📝 Summary:
Virtual try-on (VTON) has advanced single-garment visualization, yet real-world fashion centers on full outfits with multiple garments, accessories, fine-grained categories, layering, and diverse styl...

🔹 Publication Date: Published on Mar 14

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.14153
• PDF: https://arxiv.org/pdf/2603.14153
• Project Page: https://artmesciencelab.github.io/Garments2Look/
• Github: https://github.com/ArtmeScienceLab/Garments2Look

✨ Datasets citing this paper:
• https://huggingface.co/datasets/ArtmeScienceLab/Garments2Look

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨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