Hot: generalAll contenthive-129948krhive-196917zzansteemhive-183959hive-185836hive-180932hive-166405hive-150122uncommonlabhive-144064hive-188619photographyhive-101145hive-183397hive-145157bitcoinhive-193637lifehive-181136krsuccesshive-184714hive-109690hive-113376TrendingNewHotLikersrahimakhatun (75)in hive-129948 • 11 hours agoসব কষ্ট কি আর শেয়ার করা যায়।আমি @rahimakhatun from Bangladesh ৬ ই পৌঁষ ১৪৩১-------- ২১ই ডিসেম্বর ২০২৪ আমার বাংলা ব্লগের সকল বাংলাভাষী সদস্যগনকে আমার সালাম এবং আদাব। সবাই কেমন আছেন ? আশা করি, সবাই মহান…abdelzaher1 (53)in ai • 6 hours agoAFlow: A Novel Artificial Intelligence Framework for Automated Workflow OptimizationA team of researchers from DeepWisdom, The Hong Kong University of Science and Technology (Guangzhou), Renmin University of China, Nanjing University, Fudan University, King Abdullah University of…abdelzaher1 (53)in ai • 18 hours agoQuanda: A New Python Toolkit for Standardized Evaluation and Benchmarking of Training Data Attribution (TDA) in Explainable AIThe Fraunhofer Institute for Telecommunications has put forth Quanda to bridge this gap. It is a Python toolkit that provides a comprehensive set of evaluation metrics and a uniform interface for…abdelzaher1 (53)in ai • 12 hours agoMentalArena: A Self-Play AI Framework Designed to Train Language Models for Diagnosis and Treatment of Mental Health DisordersThe current AI-based mental health systems rely on template-driven or decision-tree-based approaches, which lack flexibility and personalization. These models are trained on data collected from…abdelzaher1 (53)in ai • yesterdaySimular Research Introduces Agent S: An Open-Source AI Framework Designed to Interact Autonomously with Computers through a Graphical User InterfaceSimular Research introduces Agent S, an open agentic framework designed to use computers like a human, specifically through autonomous interaction with GUIs. This framework aims to transform…abdelzaher1 (53)in ai • yesterdayMIBench: A Comprehensive AI Benchmark for Model Inversion Attack and DefenseUntil now it was very hard to find any such benchmark that could measure a model‚Äôs potential to defend itself against such threats. Although to defend against MI attacks, most existing methods can…abdelzaher1 (53)in ai • yesterdayZyphra Releases Zamba2-7B: A State-of-the-Art Small Language ModelThe architecture of Zamba2-7B incorporates significant technical innovations that enhance both efficiency and expressivity. Unlike its predecessor, Zamba1, Zamba2-7B uses two shared attention blocks…abdelzaher1 (53)in ai • 2 days agoInheritune: An Effective AI Training Approach for Developing Smaller and High-Performing Language ModelsVarious studies have explored attention degeneration, primarily focusing on attention rank and entropy collapse, which cause representation issues and training instability. Previous research has…abdelzaher1 (53)in ai • 2 days agoStanford Researchers Propose LoLCATS: A Cutting Edge AI Method for Efficient LLM LinearizationResearchers from Stanford University, Together AI, California Institute of Technology, and MIT introduced LoLCATS (Low-rank Linear Conversion via Attention Transfer). LoLCATS is a two-step method…abdelzaher1 (53)in ai • 2 days agoThis AI Paper by MIT Introduces Adaptive Computation for Efficient and Cost-Effective Language ModelsOne of the major issues in the current approach to language models is that they use a fixed computational procedure for every input, regardless of the difficulty. This approach wastes resources on…abdelzaher1 (53)in ai • 3 days agoResearchers from UCLA and Stanford Introduce MRAG-Bench: An AI Benchmark Specifically Designed for Vision-Centric Evaluation for Retrieval-Augmented Multimodal ModelsResearchers from UCLA and Stanford introduced MRAG-Bench, a vision-centric benchmark designed to evaluate the effectiveness of LVLMs in scenarios where visual information provides a clear advantage…abdelzaher1 (53)in ai • 3 days agoOPEN-RAG: A Novel AI Framework Designed to Enhance Reasoning Capabilities in RAG with Open-Source LLMsResearchers from Bangladesh University of Engineering and Technology, University of North Texas, York University, Canada, Salesforce Research, Qatar Computing Research Institute (QCRI), Fatima…abdelzaher1 (53)in ai • 3 days agoMeet Arch: The Intelligent Layer 7 Gateway for LLM ApplicationsMeet Arch: An intelligent Layer 7 gateway designed to protect, observe, and personalize LLM applications (agents, assistants, co-pilots) with your APIs. Arch serves as the connective tissue that…abdelzaher1 (53)in ai • 3 days agoGoogle DeepMind Research Introduces Diversity-Rewarded CFG Distillation: A Novel Finetuning Approach to Enhance the Quality-Diversity Trade-off in Generative AI ModelsExisting methods like Classifier-free guidance (CFG) have been widely applied to domains like image, video, and audio generation. However, its negative impact on diversity limits its usefulness in…abdelzaher1 (53)in ai • 4 days agoSalesforce AI Research Proposes Dataset-Driven Verifier to Improve LLM Reasoning ConsistencyResearchers from the University of Notre Dame and Salesforce AI introduce an innovative framework that scales up inference-time computation by generating multiple reasoning paths for complex tasks.…limon88 (74)in hive-129948 • 4 days agoআমরা সবাই ক্ষণিকের অতিথি মাত্র।আমরা সবাই ক্ষণিকের অতিথি মাত্র। "সবার সুস্বাস্থ্য কামনা করছি" "ছবিটি Canva দিয়ে তৈরি" হ্যালো বন্ধুরা 💞 আমার বাংলা ব্লগ পরিবার। প্রথমেই সবাইকে আমার সালাম ও আদাব। কেমন আছেন…abdelzaher1 (53)in ai • 4 days agoOpenR: An Open-Source AI Framework Enhancing Reasoning in Large Language ModelsResearchers from University College London, the University of Liverpool, Shanghai Jiao Tong University, The Hong Kong University of Science and Technology (Guangzhou), and Westlake University…abdelzaher1 (53)in ai • 4 days agoHolistic Evaluation of Vision Language Models (VHELM): Extending the HELM Framework to VLMsThe current methods for the evaluation of VLMs include isolated tasks like image captioning, VQA, and image generation. Benchmarks like A-OKVQA and VizWiz are specialized in the limited practice of…abdelzaher1 (53)in ai • 4 days agoNVIDIA AI Researchers Explore Upcycling Large Language Models into Sparse Mixture-of-ExpertsA common problem faced by dense models is that they can reach a performance plateau, particularly when working with models that have already been extensively trained. Once a dense model has reached…abdelzaher1 (53)in ai • 5 days agoF5-TTS: A Fully Non-Autoregressive Text-to-Speech System based on Flow Matching with Diffusion Transformer (DiT)Researchers from Shanghai Jiao Tong University, the University of Cambridge, and Geely Automobile Research Institute introduced F5-TTS, a non-autoregressive text-to-speech (TTS) system that utilizes…
