✨MADD: Multi-Agent Drug Discovery Orchestra
📝 Summary:
MADD is a multi-agent system integrating LLMs and specialized models to enhance hit identification in drug discovery. It builds customized pipelines from natural language queries, demonstrating superior performance and accessibility for researchers.
🔹 Publication Date: Published on Nov 11
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.08217
• PDF: https://arxiv.org/pdf/2511.08217
• Github: https://github.com/sb-ai-lab/MADD
✨ Datasets citing this paper:
• https://huggingface.co/datasets/ITMO-NSS/MADD_Benchmark_and_results
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
#DrugDiscovery #MultiAgentSystems #LLMs #AI #AIforScience
📝 Summary:
MADD is a multi-agent system integrating LLMs and specialized models to enhance hit identification in drug discovery. It builds customized pipelines from natural language queries, demonstrating superior performance and accessibility for researchers.
🔹 Publication Date: Published on Nov 11
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.08217
• PDF: https://arxiv.org/pdf/2511.08217
• Github: https://github.com/sb-ai-lab/MADD
✨ Datasets citing this paper:
• https://huggingface.co/datasets/ITMO-NSS/MADD_Benchmark_and_results
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
#DrugDiscovery #MultiAgentSystems #LLMs #AI #AIforScience
❤1
✨Black-Box On-Policy Distillation of Large Language Models
📝 Summary:
Generative Adversarial Distillation GAD is a new black-box on-policy method for distilling LLMs. GAD trains a student generator and a discriminator for adaptive feedback, surpassing traditional distillation. It enables student LLMs to perform comparably to proprietary teachers.
🔹 Publication Date: Published on Nov 13
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.10643
• PDF: https://arxiv.org/pdf/2511.10643
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
#LLMs #AIDistillation #MachineLearning #GenerativeAI #DeepLearning
📝 Summary:
Generative Adversarial Distillation GAD is a new black-box on-policy method for distilling LLMs. GAD trains a student generator and a discriminator for adaptive feedback, surpassing traditional distillation. It enables student LLMs to perform comparably to proprietary teachers.
🔹 Publication Date: Published on Nov 13
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.10643
• PDF: https://arxiv.org/pdf/2511.10643
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
#LLMs #AIDistillation #MachineLearning #GenerativeAI #DeepLearning
✨AlphaResearch: Accelerating New Algorithm Discovery with Language Models
📝 Summary:
AlphaResearch is an autonomous agent that discovers new algorithms using a dual research environment. It achieved a 2/8 win rate against human researchers and found a best-of-known solution for the packing circles problem, showing LLMs potential for algorithm discovery.
🔹 Publication Date: Published on Nov 11
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.08522
• PDF: https://arxiv.org/pdf/2511.08522
• Github: https://github.com/answers111/alpha-research
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
#AlgorithmDiscovery #LLMs #AIResearch #AutonomousAgents #MachineLearning
📝 Summary:
AlphaResearch is an autonomous agent that discovers new algorithms using a dual research environment. It achieved a 2/8 win rate against human researchers and found a best-of-known solution for the packing circles problem, showing LLMs potential for algorithm discovery.
🔹 Publication Date: Published on Nov 11
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.08522
• PDF: https://arxiv.org/pdf/2511.08522
• Github: https://github.com/answers111/alpha-research
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
#AlgorithmDiscovery #LLMs #AIResearch #AutonomousAgents #MachineLearning
❤1
✨Hail to the Thief: Exploring Attacks and Defenses in Decentralised GRPO
📝 Summary:
This study identifies and demonstrates adversarial attacks in decentralized GRPO for LLMs, achieving 100% success rates by injecting malicious tokens. It also proposes effective defense mechanisms that can stop these attacks completely.
🔹 Publication Date: Published on Nov 12
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.09780
• PDF: https://arxiv.org/pdf/2511.09780
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
#LLMs #AdversarialAttacks #AISecurity #DecentralizedAI #GRPO
📝 Summary:
This study identifies and demonstrates adversarial attacks in decentralized GRPO for LLMs, achieving 100% success rates by injecting malicious tokens. It also proposes effective defense mechanisms that can stop these attacks completely.
🔹 Publication Date: Published on Nov 12
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.09780
• PDF: https://arxiv.org/pdf/2511.09780
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
#LLMs #AdversarialAttacks #AISecurity #DecentralizedAI #GRPO
❤1
✨DoPE: Denoising Rotary Position Embedding
📝 Summary:
DoPE improves Transformer length generalization by detecting and mitigating noisy frequency bands in positional embeddings. This training-free method enhances retrieval accuracy and reasoning stability across extended contexts up to 64K tokens.
🔹 Publication Date: Published on Nov 12
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.09146
• PDF: https://arxiv.org/pdf/2511.09146
• Project Page: https://The-physical-picture-of-LLMs.github.io
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
#Transformers #PositionalEmbedding #LLMs #DeepLearning #AIResearch
📝 Summary:
DoPE improves Transformer length generalization by detecting and mitigating noisy frequency bands in positional embeddings. This training-free method enhances retrieval accuracy and reasoning stability across extended contexts up to 64K tokens.
🔹 Publication Date: Published on Nov 12
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.09146
• PDF: https://arxiv.org/pdf/2511.09146
• Project Page: https://The-physical-picture-of-LLMs.github.io
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
#Transformers #PositionalEmbedding #LLMs #DeepLearning #AIResearch
✨Uni-MoE-2.0-Omni: Scaling Language-Centric Omnimodal Large Model with Advanced MoE, Training and Data
📝 Summary:
Uni-MoE 2.0-Omni is an open-source omnimodal large model improving multimodal understanding, reasoning, and generation. It uses dynamic MoE and progressive training to achieve state-of-the-art results across 85 benchmarks, outperforming leading models like Qwen2.5-Omni.
🔹 Publication Date: Published on Nov 16
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.12609
• PDF: https://arxiv.org/pdf/2511.12609
• Project Page: https://idealistxy.github.io/Uni-MoE-v2.github.io/
• Github: https://github.com/HITsz-TMG/Uni-MoE
🔹 Models citing this paper:
• https://huggingface.co/HIT-TMG/Uni-MoE-2.0-Omni
• https://huggingface.co/HIT-TMG/Uni-MoE-2.0-Base
• https://huggingface.co/HIT-TMG/Uni-MoE-2.0-Image
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
#OmnimodalAI #LLMs #MixtureOfExperts #MultimodalLearning #AIResearch
📝 Summary:
Uni-MoE 2.0-Omni is an open-source omnimodal large model improving multimodal understanding, reasoning, and generation. It uses dynamic MoE and progressive training to achieve state-of-the-art results across 85 benchmarks, outperforming leading models like Qwen2.5-Omni.
🔹 Publication Date: Published on Nov 16
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.12609
• PDF: https://arxiv.org/pdf/2511.12609
• Project Page: https://idealistxy.github.io/Uni-MoE-v2.github.io/
• Github: https://github.com/HITsz-TMG/Uni-MoE
🔹 Models citing this paper:
• https://huggingface.co/HIT-TMG/Uni-MoE-2.0-Omni
• https://huggingface.co/HIT-TMG/Uni-MoE-2.0-Base
• https://huggingface.co/HIT-TMG/Uni-MoE-2.0-Image
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
#OmnimodalAI #LLMs #MixtureOfExperts #MultimodalLearning #AIResearch
✨Souper-Model: How Simple Arithmetic Unlocks State-of-the-Art LLM Performance
📝 Summary:
SoCE is a novel model souping technique that boosts LLM performance. It uses non-uniform weighted averaging of expert models identified for specific benchmark categories, unlike uniform methods. This leads to state-of-the-art results and improved robustness.
🔹 Publication Date: Published on Nov 17
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.13254
• PDF: https://arxiv.org/pdf/2511.13254
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
#LLMs #ModelSouping #MachineLearning #AI #StateOfTheArt
📝 Summary:
SoCE is a novel model souping technique that boosts LLM performance. It uses non-uniform weighted averaging of expert models identified for specific benchmark categories, unlike uniform methods. This leads to state-of-the-art results and improved robustness.
🔹 Publication Date: Published on Nov 17
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.13254
• PDF: https://arxiv.org/pdf/2511.13254
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
#LLMs #ModelSouping #MachineLearning #AI #StateOfTheArt
✨Instella: Fully Open Language Models with Stellar Performance
📝 Summary:
Instella is a family of fully open language models trained on open data. It achieves state-of-the-art among fully open models and competes with leading open-weight LLMs. Specialized variants for long context and math reasoning are also offered.
🔹 Publication Date: Published on Nov 13
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.10628
• PDF: https://arxiv.org/pdf/2511.10628
• Github: https://github.com/AMD-AGI/Instella
🔹 Models citing this paper:
• https://huggingface.co/amd/AMD-OLMo
• https://huggingface.co/amd/Instella-3B-Instruct
• https://huggingface.co/amd/Instella-3B
✨ Datasets citing this paper:
• https://huggingface.co/datasets/amd/Instella-Long
• https://huggingface.co/datasets/amd/Instella-GSM8K-synthetic
✨ Spaces citing this paper:
• https://huggingface.co/spaces/DexterSptizu/AMD-OLMo-1B
• https://huggingface.co/spaces/universeofml/DeepFocusTrain
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
#LLMs #OpenSource #AI #MachineLearning #NLP
📝 Summary:
Instella is a family of fully open language models trained on open data. It achieves state-of-the-art among fully open models and competes with leading open-weight LLMs. Specialized variants for long context and math reasoning are also offered.
🔹 Publication Date: Published on Nov 13
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.10628
• PDF: https://arxiv.org/pdf/2511.10628
• Github: https://github.com/AMD-AGI/Instella
🔹 Models citing this paper:
• https://huggingface.co/amd/AMD-OLMo
• https://huggingface.co/amd/Instella-3B-Instruct
• https://huggingface.co/amd/Instella-3B
✨ Datasets citing this paper:
• https://huggingface.co/datasets/amd/Instella-Long
• https://huggingface.co/datasets/amd/Instella-GSM8K-synthetic
✨ Spaces citing this paper:
• https://huggingface.co/spaces/DexterSptizu/AMD-OLMo-1B
• https://huggingface.co/spaces/universeofml/DeepFocusTrain
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
#LLMs #OpenSource #AI #MachineLearning #NLP
arXiv.org
Instella: Fully Open Language Models with Stellar Performance
Large language models (LLMs) have demonstrated remarkable performance across a wide range of tasks, yet the majority of high-performing models remain closed-source or partially open, limiting...
❤1
✨Evolve the Method, Not the Prompts: Evolutionary Synthesis of Jailbreak Attacks on LLMs
📝 Summary:
EvoSynth is a new framework that autonomously engineers and evolves novel, code-based jailbreak methods for LLMs, moving beyond prompt refinement. It uses self-correction to create diverse and highly successful attacks, achieving 85.5% ASR against robust models.
🔹 Publication Date: Published on Nov 16
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.12710
• PDF: https://arxiv.org/pdf/2511.12710
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
#LLMs #JailbreakAttacks #AISecurity #EvolutionaryAlgorithms #AIResearch
📝 Summary:
EvoSynth is a new framework that autonomously engineers and evolves novel, code-based jailbreak methods for LLMs, moving beyond prompt refinement. It uses self-correction to create diverse and highly successful attacks, achieving 85.5% ASR against robust models.
🔹 Publication Date: Published on Nov 16
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.12710
• PDF: https://arxiv.org/pdf/2511.12710
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
#LLMs #JailbreakAttacks #AISecurity #EvolutionaryAlgorithms #AIResearch
❤1
✨Genomic Next-Token Predictors are In-Context Learners
📝 Summary:
In-context learning ICL emerges organically in genomic sequences through large-scale predictive training, mirroring its behavior in language models. This first evidence suggests ICL is a general phenomenon of large-scale modeling, not exclusive to human language.
🔹 Publication Date: Published on Nov 16
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.12797
• PDF: https://arxiv.org/pdf/2511.12797
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
#Genomics #InContextLearning #AI #MachineLearning #LLMs
📝 Summary:
In-context learning ICL emerges organically in genomic sequences through large-scale predictive training, mirroring its behavior in language models. This first evidence suggests ICL is a general phenomenon of large-scale modeling, not exclusive to human language.
🔹 Publication Date: Published on Nov 16
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.12797
• PDF: https://arxiv.org/pdf/2511.12797
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
#Genomics #InContextLearning #AI #MachineLearning #LLMs
❤1
✨Error-Driven Scene Editing for 3D Grounding in Large Language Models
📝 Summary:
DEER-3D improves 3D LLM grounding by iteratively editing and retraining models. It diagnoses predicate-level errors, then generates targeted 3D scene edits as counterfactuals to enhance spatial understanding and accuracy.
🔹 Publication Date: Published on Nov 18
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.14086
• PDF: https://arxiv.org/pdf/2511.14086
• Github: https://github.com/zhangyuejoslin/Deer-3D
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
#LLMs #3DGrounding #ComputerVision #DeepLearning #AIResearch
📝 Summary:
DEER-3D improves 3D LLM grounding by iteratively editing and retraining models. It diagnoses predicate-level errors, then generates targeted 3D scene edits as counterfactuals to enhance spatial understanding and accuracy.
🔹 Publication Date: Published on Nov 18
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.14086
• PDF: https://arxiv.org/pdf/2511.14086
• Github: https://github.com/zhangyuejoslin/Deer-3D
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
#LLMs #3DGrounding #ComputerVision #DeepLearning #AIResearch
✨Agent READMEs: An Empirical Study of Context Files for Agentic Coding
📝 Summary:
This study analyzed 2303 agent context files, finding them complex and evolving like config code. Developers prioritize functional details but rarely specify non-functional requirements like security or performance. This suggests a gap in guardrails for agent-written code quality.
🔹 Publication Date: Published on Nov 17
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.12884
• PDF: https://arxiv.org/pdf/2511.12884
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
#AIAgents #SoftwareEngineering #CodeQuality #LLMs #AIResearch
📝 Summary:
This study analyzed 2303 agent context files, finding them complex and evolving like config code. Developers prioritize functional details but rarely specify non-functional requirements like security or performance. This suggests a gap in guardrails for agent-written code quality.
🔹 Publication Date: Published on Nov 17
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.12884
• PDF: https://arxiv.org/pdf/2511.12884
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
#AIAgents #SoftwareEngineering #CodeQuality #LLMs #AIResearch
✨OmniZip: Audio-Guided Dynamic Token Compression for Fast Omnimodal Large Language Models
📝 Summary:
OmniZip is a training-free framework that addresses the computational bottleneck in omnimodal LLMs by dynamically compressing audio-visual tokens. It uses audio retention scores to guide video token pruning, achieving 3.42X inference speedup and 1.4X memory reduction without performance loss.
🔹 Publication Date: Published on Nov 18
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.14582
• PDF: https://arxiv.org/pdf/2511.14582
• Github: https://github.com/KD-TAO/OmniZip
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
#OmnimodalLLM #TokenCompression #LLMs #AI #ModelEfficiency
📝 Summary:
OmniZip is a training-free framework that addresses the computational bottleneck in omnimodal LLMs by dynamically compressing audio-visual tokens. It uses audio retention scores to guide video token pruning, achieving 3.42X inference speedup and 1.4X memory reduction without performance loss.
🔹 Publication Date: Published on Nov 18
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.14582
• PDF: https://arxiv.org/pdf/2511.14582
• Github: https://github.com/KD-TAO/OmniZip
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
#OmnimodalLLM #TokenCompression #LLMs #AI #ModelEfficiency
✨Uni-MoE: Scaling Unified Multimodal LLMs with Mixture of Experts
📝 Summary:
Uni-MoE introduces a sparse Multimodal Mixture of Experts LLM efficiently handling diverse data types. It uses modality-specific encoders and a progressive training strategy, reducing performance bias and improving collaboration across modalities.
🔹 Publication Date: Published on May 18, 2024
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2405.11273
• PDF: https://arxiv.org/pdf/2405.11273
• Github: https://github.com/hitsz-tmg/umoe-scaling-unified-multimodal-llms
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
#MultimodalAI #LLMs #MixtureOfExperts #DeepLearning #AIResearch
📝 Summary:
Uni-MoE introduces a sparse Multimodal Mixture of Experts LLM efficiently handling diverse data types. It uses modality-specific encoders and a progressive training strategy, reducing performance bias and improving collaboration across modalities.
🔹 Publication Date: Published on May 18, 2024
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2405.11273
• PDF: https://arxiv.org/pdf/2405.11273
• Github: https://github.com/hitsz-tmg/umoe-scaling-unified-multimodal-llms
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
#MultimodalAI #LLMs #MixtureOfExperts #DeepLearning #AIResearch
✨FreeAskWorld: An Interactive and Closed-Loop Simulator for Human-Centric Embodied AI
📝 Summary:
FreeAskWorld is an interactive simulator using LLMs for human-centric embodied AI with complex social behaviors. It offers a large dataset, improving agent semantic understanding and interaction competency, highlighting interaction as a key information modality.
🔹 Publication Date: Published on Nov 17
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.13524
• PDF: https://arxiv.org/pdf/2511.13524
• Github: https://github.com/AIR-DISCOVER/FreeAskWorld
✨ Datasets citing this paper:
• https://huggingface.co/datasets/Astronaut-PENG/FreeAskWorld
• https://huggingface.co/datasets/Astronaut-PENG/FreeWorld
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
#EmbodiedAI #LLMs #AISimulation #HumanAI #AIResearch
📝 Summary:
FreeAskWorld is an interactive simulator using LLMs for human-centric embodied AI with complex social behaviors. It offers a large dataset, improving agent semantic understanding and interaction competency, highlighting interaction as a key information modality.
🔹 Publication Date: Published on Nov 17
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.13524
• PDF: https://arxiv.org/pdf/2511.13524
• Github: https://github.com/AIR-DISCOVER/FreeAskWorld
✨ Datasets citing this paper:
• https://huggingface.co/datasets/Astronaut-PENG/FreeAskWorld
• https://huggingface.co/datasets/Astronaut-PENG/FreeWorld
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
#EmbodiedAI #LLMs #AISimulation #HumanAI #AIResearch
✨GraphGen: Enhancing Supervised Fine-Tuning for LLMs with Knowledge-Driven Synthetic Data Generation
📝 Summary:
GraphGen is a framework that enhances synthetic data generation for LLMs by constructing fine-grained knowledge graphs. It targets high-value knowledge gaps, uses multi-hop sampling, and style-controlled generation to create diverse and accurate QA pairs. This approach outperforms conventional me...
🔹 Publication Date: Published on May 26
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2505.20416
• PDF: https://arxiv.org/pdf/2505.20416
• Project Page: https://huggingface.co/spaces/chenzihong/GraphGen
• Github: https://github.com/open-sciencelab/GraphGen
✨ Datasets citing this paper:
• https://huggingface.co/datasets/chenzihong/GraphGen-Data
✨ Spaces citing this paper:
• https://huggingface.co/spaces/chenzihong/GraphGen
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
#LLMs #KnowledgeGraphs #SyntheticData #FineTuning #NLP
📝 Summary:
GraphGen is a framework that enhances synthetic data generation for LLMs by constructing fine-grained knowledge graphs. It targets high-value knowledge gaps, uses multi-hop sampling, and style-controlled generation to create diverse and accurate QA pairs. This approach outperforms conventional me...
🔹 Publication Date: Published on May 26
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2505.20416
• PDF: https://arxiv.org/pdf/2505.20416
• Project Page: https://huggingface.co/spaces/chenzihong/GraphGen
• Github: https://github.com/open-sciencelab/GraphGen
✨ Datasets citing this paper:
• https://huggingface.co/datasets/chenzihong/GraphGen-Data
✨ Spaces citing this paper:
• https://huggingface.co/spaces/chenzihong/GraphGen
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
#LLMs #KnowledgeGraphs #SyntheticData #FineTuning #NLP
✨Skywork R1V: Pioneering Multimodal Reasoning with Chain-of-Thought
📝 Summary:
Skywork R1V is a multimodal reasoning model that efficiently extends large language models to visual tasks. It achieves this via efficient transfer, enhanced visual-text alignment, and adaptive Chain-of-Thought optimization, delivering competitive benchmark performance.
🔹 Publication Date: Published on Apr 8
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2504.05599
• PDF: https://arxiv.org/pdf/2504.05599
• Project Page: https://huggingface.co/papers?q=lightweight%20visual%20projector
• Github: https://github.com/SkyworkAI/Skywork-R1V
🔹 Models citing this paper:
• https://huggingface.co/Skywork/Skywork-R1V-38B
• https://huggingface.co/Skywork/Skywork-R1V2-38B
• https://huggingface.co/Skywork/Skywork-R1V2-38B-AWQ
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
#MultimodalAI #ChainOfThought #LLMs #ComputerVision #AIResearch
📝 Summary:
Skywork R1V is a multimodal reasoning model that efficiently extends large language models to visual tasks. It achieves this via efficient transfer, enhanced visual-text alignment, and adaptive Chain-of-Thought optimization, delivering competitive benchmark performance.
🔹 Publication Date: Published on Apr 8
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2504.05599
• PDF: https://arxiv.org/pdf/2504.05599
• Project Page: https://huggingface.co/papers?q=lightweight%20visual%20projector
• Github: https://github.com/SkyworkAI/Skywork-R1V
🔹 Models citing this paper:
• https://huggingface.co/Skywork/Skywork-R1V-38B
• https://huggingface.co/Skywork/Skywork-R1V2-38B
• https://huggingface.co/Skywork/Skywork-R1V2-38B-AWQ
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
#MultimodalAI #ChainOfThought #LLMs #ComputerVision #AIResearch
👍1
✨OpenMMReasoner: Pushing the Frontiers for Multimodal Reasoning with an Open and General Recipe
📝 Summary:
OpenMMReasoner introduces a two-stage SFT+RL training approach with rigorous data curation. This method significantly enhances multimodal reasoning, improving performance by 11.6% over baselines across nine benchmarks.
🔹 Publication Date: Published on Nov 20
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.16334
• PDF: https://arxiv.org/pdf/2511.16334
• Project Page: https://evolvinglmms-lab.github.io/OpenMMReasoner/
• Github: https://github.com/EvolvingLMMs-Lab/OpenMMReasoner
🔹 Models citing this paper:
• https://huggingface.co/OpenMMReasoner/OpenMMReasoner-RL
• https://huggingface.co/OpenMMReasoner/OpenMMReasoner-ColdStart
✨ Datasets citing this paper:
• https://huggingface.co/datasets/OpenMMReasoner/OpenMMReasoner-SFT-874K
• https://huggingface.co/datasets/OpenMMReasoner/OpenMMReasoner-RL-74K
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
#MultimodalAI #ReinforcementLearning #LLMs #AIResearch #DeepLearning
📝 Summary:
OpenMMReasoner introduces a two-stage SFT+RL training approach with rigorous data curation. This method significantly enhances multimodal reasoning, improving performance by 11.6% over baselines across nine benchmarks.
🔹 Publication Date: Published on Nov 20
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.16334
• PDF: https://arxiv.org/pdf/2511.16334
• Project Page: https://evolvinglmms-lab.github.io/OpenMMReasoner/
• Github: https://github.com/EvolvingLMMs-Lab/OpenMMReasoner
🔹 Models citing this paper:
• https://huggingface.co/OpenMMReasoner/OpenMMReasoner-RL
• https://huggingface.co/OpenMMReasoner/OpenMMReasoner-ColdStart
✨ Datasets citing this paper:
• https://huggingface.co/datasets/OpenMMReasoner/OpenMMReasoner-SFT-874K
• https://huggingface.co/datasets/OpenMMReasoner/OpenMMReasoner-RL-74K
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
#MultimodalAI #ReinforcementLearning #LLMs #AIResearch #DeepLearning
arXiv.org
OpenMMReasoner: Pushing the Frontiers for Multimodal Reasoning...
Recent advancements in large reasoning models have fueled growing interest in extending such capabilities to multimodal domains. However, despite notable progress in visual reasoning, the lack of...
❤1
✨WorldGen: From Text to Traversable and Interactive 3D Worlds
📝 Summary:
WorldGen transforms text prompts into interactive 3D worlds. It combines LLM reasoning with procedural and diffusion-based 3D generation to efficiently create coherent, navigable environments for gaming and simulation.
🔹 Publication Date: Published on Nov 20
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.16825
• PDF: https://arxiv.org/pdf/2511.16825
• Project Page: https://www.meta.com/blog/worldgen-3d-world-generation-reality-labs-generative-ai-research/
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
#3DGeneration #GenerativeAI #LLMs #VirtualWorlds #AIResearch
📝 Summary:
WorldGen transforms text prompts into interactive 3D worlds. It combines LLM reasoning with procedural and diffusion-based 3D generation to efficiently create coherent, navigable environments for gaming and simulation.
🔹 Publication Date: Published on Nov 20
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.16825
• PDF: https://arxiv.org/pdf/2511.16825
• Project Page: https://www.meta.com/blog/worldgen-3d-world-generation-reality-labs-generative-ai-research/
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
#3DGeneration #GenerativeAI #LLMs #VirtualWorlds #AIResearch
✨Parrot: Persuasion and Agreement Robustness Rating of Output Truth -- A Sycophancy Robustness Benchmark for LLMs
📝 Summary:
PARROT evaluates LLM robustness to sycophancy by comparing neutral and false authoritative questions. Advanced models resist pressure well, but older ones show severe epistemic collapse, even reducing confidence in correct answers. This highlights the need for LLMs to resist pressure for safe dep...
🔹 Publication Date: Published on Nov 21
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.17220
• PDF: https://arxiv.org/pdf/2511.17220
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
#LLMs #AISafety #ModelRobustness #Sycophancy #AIResearch
📝 Summary:
PARROT evaluates LLM robustness to sycophancy by comparing neutral and false authoritative questions. Advanced models resist pressure well, but older ones show severe epistemic collapse, even reducing confidence in correct answers. This highlights the need for LLMs to resist pressure for safe dep...
🔹 Publication Date: Published on Nov 21
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.17220
• PDF: https://arxiv.org/pdf/2511.17220
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
#LLMs #AISafety #ModelRobustness #Sycophancy #AIResearch
❤1