✨MTR-DuplexBench: Towards a Comprehensive Evaluation of Multi-Round Conversations for Full-Duplex Speech Language Models

📝 Summary:
Current full-duplex speech language models struggle with multi-round conversations due to inconsistent performance across different evaluation dimensions, necessitating comprehensive benchmarking. AI-...

🔹 Publication Date: Published on Apr 17

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.10262
• PDF: https://arxiv.org/pdf/2511.10262
• Github: https://github.com/ZhangHe0918/MTR-DuplexBench

✨ Datasets citing this paper:
• https://huggingface.co/datasets/Jeff0918/MTR-DuplexBench

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨The Continuity Layer: Why Intelligence Needs an Architecture for What It Carries Forward

📝 Summary:
The paper advocates for a continuity layer in AI systems to address the limitation of transient understanding, proposing a Decomposed Trace Convergence Memory storage primitive and a four-layer develo...

🔹 Publication Date: Published on Apr 19

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.17273
• PDF: https://arxiv.org/pdf/2604.17273
• Project Page: https://kenoticlabs.com/thesis
• Github: https://github.com/Kenotic-Labs/continuity-layer

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Significance and Stability Analysis of Gene-Environment Interaction using RGxEStat

📝 Summary:
G e n o t y p e - b y - E n v i r o n m e n t ( G x E ) i n t e r a c t i o n s i n f l u e n c e t h e p e r f o r m a n c e o f g e n o t y p e s a c r o s s d i v e r s e e n v i r o n m e n t s , ...

🔹 Publication Date: Published on Apr 3

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.03337
• PDF: https://arxiv.org/pdf/2604.03337
• Github: https://github.com/mason-ching/RGxEStat

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨On the Reliability of Computer Use Agents

📝 Summary:
Computer-use agents exhibit unreliable performance due to execution stochasticity, task specification ambiguity, and behavioral variability, necessitating repeated evaluation and stable strategies for...

🔹 Publication Date: Published on Apr 20

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.17849
• PDF: https://arxiv.org/pdf/2604.17849
• Github: https://github.com/simular-ai/cua_reliability

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨The Illusion of Certainty: Decoupling Capability and Calibration in On-Policy Distillation

📝 Summary:
On-policy distillation suffers from miscalibration due to information mismatch between training and deployment contexts, which is addressed through a calibration-aware framework that improves both per...

🔹 Publication Date: Published on Apr 18

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.16830
• PDF: https://arxiv.org/pdf/2604.16830
• Project Page: https://github.com/SalesforceAIResearch/CaOPD
• Github: https://github.com/SalesforceAIResearch/CaOPD

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Forge-UGC: FX optimization and register-graph engine for universal graph compiler

📝 Summary:
Forge-UGC is a four-phase compiler for efficient transformer deployment on heterogeneous hardware, offering faster compilation, reduced inference latency, and lower energy consumption compared to exis...

🔹 Publication Date: Published on Apr 14

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.16498
• PDF: https://arxiv.org/pdf/2604.16498

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Protecting Language Models Against Unauthorized Distillation through Trace Rewriting

📝 Summary:
Techniques for modifying teacher-generated reasoning traces to prevent unauthorized knowledge distillation while maintaining answer correctness and enabling detectable watermarks are presented. AI-gen...

🔹 Publication Date: Published on Apr 16

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.15143
• PDF: https://arxiv.org/pdf/2602.15143
• Github: https://github.com/xhOwenMa/trace-rewriting

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Symbolic Guardrails for Domain-Specific Agents: Stronger Safety and Security Guarantees Without Sacrificing Utility

📝 Summary:
Symbolic guardrails provide strong safety and security guarantees for AI agents in high-stakes environments. A study found these guardrails can enforce 74% of specified policy requirements, improving safety without sacrificing utility. This makes them a practical solution for domain-specific agents.

🔹 Publication Date: Published on Apr 16

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.15579
• PDF: https://arxiv.org/pdf/2604.15579
• Github: https://github.com/hyn0027/agent-symbolic-guardrails

✨ Datasets citing this paper:
• https://huggingface.co/datasets/hyn0027D/agent-symbolic-guardrails

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨When Background Matters: Breaking Medical Vision Language Models by Transferable Attack

📝 Summary:
MedFocusLeak enables transferable black-box attacks on vision-language models for medical imaging by injecting imperceptible perturbations that redirect model attention, demonstrating significant vuln...

🔹 Publication Date: Published on Apr 19

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.17318
• PDF: https://arxiv.org/pdf/2604.17318
• Project Page: https://akashghosh.github.io/MedFocusLeakACL/
• Github: https://github.com/AkashGhosh/When-Background-Matters-Breaking-Medical-Vision-Language-Models-by-Transferable-Attack

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨MARCO: Navigating the Unseen Space of Semantic Correspondence

📝 Summary:
MARCO is a compact, fast model for semantic correspondence that excels at generalizing to unseen keypoints. Its coarse-to-fine objective and self-distillation framework improve fine-grained localization and overall accuracy.

🔹 Publication Date: Published on Apr 20

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.18267
• PDF: https://arxiv.org/pdf/2604.18267
• Project Page: https://visinf.github.io/MARCO
• Github: https://github.com/visinf/MARCO

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨River-LLM: Large Language Model Seamless Exit Based on KV Share

📝 Summary:
River-LLM enables efficient token-level early exit in LLMs by introducing a KV-Shared Exit River. This mechanism naturally generates and preserves missing historical states, overcoming the KV Cache Absence problem. It achieves 1.71 to 2.16 times practical speedup while maintaining high generation...

🔹 Publication Date: Published on Apr 20

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.18396
• PDF: https://arxiv.org/pdf/2604.18396

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Terminal Wrench: A Dataset of 331 Reward-Hackable Environments and 3,632 Exploit Trajectories

📝 Summary:
A dataset of 331 terminal-agent environments with 3,632 reward-hacking trajectories and 2,352 legitimate baselines across four AI models is released to study adversarial exploits in system administrat...

🔹 Publication Date: Published on Apr 19

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.17596
• PDF: https://arxiv.org/pdf/2604.17596
• Project Page: https://github.com/few-sh/terminal-wrench
• Github: https://github.com/few-sh/terminal-wrench

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨KWBench: Measuring Unprompted Problem Recognition in Knowledge Work

📝 Summary:
KWBench is a new benchmark for evaluating LLMs ability to recognize underlying game-theoretic structures in professional scenarios without prompts. It tests if models can identify the problem type from raw inputs alone. Current LLMs perform poorly, failing to recognize problems even if they can a...

🔹 Publication Date: Published on Apr 17

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.15760
• PDF: https://arxiv.org/pdf/2604.15760
• Project Page: https://kwbench.github.io/
• Github: https://github.com/ankitmaloo/fasteval

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨AgentSPEX: An Agent SPecification and EXecution Language

📝 Summary:
AgentSPEX is a domain-specific language and framework for creating structured, modular, and interpretable large language model agent workflows with explicit control flow and state management. AI-gener...

🔹 Publication Date: Published on Apr 14

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.13346
• PDF: https://arxiv.org/pdf/2604.13346
• Project Page: https://agentspex.ai/
• Github: https://github.com/ScaleML/AgentSPEX

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨CoInteract: Physically-Consistent Human-Object Interaction Video Synthesis via Spatially-Structured Co-Generation

📝 Summary:
CoInteract presents an end-to-end framework for human-object interaction video synthesis using a Diffusion Transformer backbone with specialized modules for structural stability and physical plausibil...

🔹 Publication Date: Published on Apr 21

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.19636
• PDF: https://arxiv.org/pdf/2604.19636
• Project Page: https://xinxiaozhe12345.github.io/CoInteract_Project/
• Github: https://github.com/luoxyhappy/CoInteract

🔹 Models citing this paper:
• https://huggingface.co/georgexin/cointeract

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨PlayCoder: Making LLM-Generated GUI Code Playable

📝 Summary:
Large language models struggle to generate logically correct GUI applications, prompting the development of PlayEval benchmark and PlayCoder framework that uses multi-agent approaches to improve funct...

🔹 Publication Date: Published on Apr 21

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.19742
• PDF: https://arxiv.org/pdf/2604.19742
• Project Page: https://arxiv.org/abs/2604.19742
• Github: https://github.com/Tencent/PlayCoder

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Dual-View Training for Instruction-Following Information Retrieval

📝 Summary:
A dual-view data synthesis approach using polarity reversal enhances retrieval systems' ability to follow instructions by training models to distinguish between topic-relevant and instruction-complian...

🔹 Publication Date: Published on Apr 20

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.18845
• PDF: https://arxiv.org/pdf/2604.18845

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Code-Switching Information Retrieval: Benchmarks, Analysis, and the Limits of Current Retrievers

📝 Summary:
Code-switching poses significant challenges for information retrieval systems, revealing performance bottlenecks and embedding space divergences that current multilingual approaches cannot fully addre...

🔹 Publication Date: Published on Apr 19

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.17632
• PDF: https://arxiv.org/pdf/2604.17632
• Github: https://github.com/paddler2022/Code-Switching-Information-Retrieval

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨LoopCTR: Unlocking the Loop Scaling Power for Click-Through Rate Prediction

📝 Summary:
LoopCTR introduces a loop scaling paradigm for CTR models that increases training computation through recursive layer reuse while maintaining efficient inference, achieving state-of-the-art performanc...

🔹 Publication Date: Published on Apr 21

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.19550
• PDF: https://arxiv.org/pdf/2604.19550

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Target-Oriented Pretraining Data Selection via Neuron-Activated Graph

📝 Summary:
A novel target-oriented language model pretraining framework uses neuron activation graphs to select informative data without additional training, demonstrating superior performance across multiple be...

🔹 Publication Date: Published on Apr 17

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.15706
• PDF: https://arxiv.org/pdf/2604.15706
• Project Page: https://asillycat.github.io/NAG-website/
• Github: https://github.com/asillycat/NAG

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Tstars-Tryon 1.0: Robust and Realistic Virtual Try-On for Diverse Fashion Items

📝 Summary:
A commercial-scale virtual try-on system achieves high success rates, photorealistic results, and real-time performance through integrated system design and multi-stage training. AI-generated summary ...

🔹 Publication Date: Published on Apr 21

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.19748
• PDF: https://arxiv.org/pdf/2604.19748
• Project Page: https://mpage.taobao.com/hd/download.html

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research