TechniqueRLHF / Alignment8 recent entries23 Sept 2026Trustworthy Agentic AI: Failure Modes, Mitigation Strategies, and a Lifecycle Framework for Autonomous LLM SystemsarXiv:2609.22712v1 Announce Type: new Abstract: Agentic AI systems built on large language models can plan over multiple steps, use external tools, retain information in memory, and coordinate with ot→24 Sept 2026How Google Cloud Networking Supports Your Fluid Compute Choices for AI WorkloadsThe availability of resources for AI workloads can be challenging across the industry, especially accelerators. This can slow your AI workload deployment if it’s built around a specific type of accele
TechniqueRAG8 recent entries26 May 2026Leveraging Spreading Activation for Improved Document Retrieval in Knowledge-Graph-Based RAG SystemsarXiv:2512.15922v3 Announce Type: replace Abstract: Despite initial successes and a variety of architectures, retrieval-augmented generation systems still struggle to reliably retrieve and connect the→6 Jun 2026Beyond Vector Similarity: A Structural Analysis of Graph-Augmented Retrieval for Industrial Knowledge GraphsarXiv:2606.06003v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) fails systematically on queries requiring structural reasoning over interconnected entities. We compare eight retri→30 Jun 2026Efficient Retrieval-Augmented Generation via Token Co-occurrence GraphsarXiv:2606.30093v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) mitigates hallucinations in Large Language Models (LLMs) by grounding the generation process on external knowledge.→29 Jul 2026Real-time Spatial Retrieval Augmented Generation for Urban EnvironmentsarXiv:2505.02271v2 Announce Type: replace Abstract: The proliferation of Generative Artificial Ingelligence (AI), especially Large Language Models, presents transformative opportunities for urban appl→30 Jul 2026Under the Hood: Serving Kimi K3DigitalOcean launched Kimi K3 on day 0. It’s already one of the most popular models on the platform and across the market: second most likes on Hugging Face, sixth most traffic on OpenCode. Getting a →18 Aug 2026Automating the Detection of Requirement Dependencies Using Large Language ModelsarXiv:2602.22456v2 Announce Type: replace-cross Abstract: Requirements are inherently interconnected through various types of dependencies. Identifying these dependencies is essential, as they underpi→5 Sept 2026Reusing old hardware for starting local ai-journey?Hi, I am thinking about putting some money / time into my local ai learning path and 'cleared' my attic where I found the following hardware. 3 x NUC11 (Core i5 1145G7 / 2,6 GHz, 64 GB RAM DDR4 2666MH→25 Sept 2026BiGraph-Diffuse: A Bidirectional Diffusion Language Model with Graph-Structured Retrieval For Mental Health CounselingarXiv:2609.29519v1 Announce Type: new Abstract: Mental health disorders affect hundreds of millions of people around the world, yet access to professional counseling remains severely limited. AI-power
TechniqueAgents8 recent entries24 Sept 2026How Google Cloud Networking Supports Your Fluid Compute Choices for AI WorkloadsThe availability of resources for AI workloads can be challenging across the industry, especially accelerators. This can slow your AI workload deployment if it’s built around a specific type of accele→24 Sept 2026A new, no-compromises database architecture for the agentic eraEntire database engineering careers have been spent on a single question: How do you scale an OLTP workload without compromising the system of record that owns the data? Exadata answered the question →29 Sept 202650B+ MoEs with few active parameters, what's the sweet spot for intelligence, agent speed, and affordable fine-tuning?I’m building a Polish General purpose legal Model that drafts documents, answers questions using legal sources, and has enough coding ability to handle some automation. The workflow is very tool-heavy→1 Oct 2026AI Agents are Vulnerable to RadicalizationarXiv:2609.38296v1 Announce Type: new Abstract: Large language models (LLMs) can influence people's beliefs, yet little is known about whether and how they can manipulate each other. To investigate th→2 Oct 2026SoK: Decentralized Agent Economic InfrastructurearXiv:2610.01756v1 Announce Type: cross Abstract: Decentralized agent economies increasingly build a single task from protocols that were designed and secured separately. This creates a simple problem→2 Oct 2026Science Utopia? Closed-Loop LLM Simulation of Academic Research EcosystemsarXiv:2610.01257v1 Announce Type: cross Abstract: Scientific progress emerges from a longitudinal ecosystem in which researchers, institutions, funding agencies, collaboration networks, and the scient→5 Oct 2026ULTRADISCOVERY: Abductive Exploration in an Interconnected, Epistemically Open UniversearXiv:2610.03092v1 Announce Type: cross Abstract: Scientific discovery often begins when scattered clues call for a new way of describing the world. Such abductive exploration can require constructing→6 Oct 2026SFlexRCA: Lightweight, Scalable, and Flexible Root Cause Analysis for IIoT Edge SystemsarXiv:2610.04893v1 Announce Type: new Abstract: Industrial Internet of Things (IIoT) systems generate high-dimensional sensor telemetry from interconnected components, where faults can propagate acros
TechniqueFine-tuning8 recent entries31 Jul 2026Towards Autonomous Aircraft Surveillance from Nanosatellites through On-Board Inference and Generative Data AugmentationarXiv:2607.28470v1 Announce Type: cross Abstract: Airborne surveillance from low Earth orbit is hindered by two interconnected bottlenecks: nanosatellites have a limited downlink budget, yet the conve→11 Aug 2026QuArch: A Benchmark for Evaluating LLM Reasoning in Computer ArchitecturearXiv:2510.22087v3 Announce Type: replace-cross Abstract: The field of computer architecture, which bridges high-level software abstractions and low-level hardware implementations, remains absent from→28 Aug 2026Graph-Guided Selective Unlearning for Language Models: Controlling Support Routes Beyond Forget SeedsarXiv:2608.26743v1 Announce Type: new Abstract: Enterprises fine-tune language models on proprietary data that may later require removal due to privacy, contractual, or compliance obligations. Selecti→15 Sept 2026Q-SiT: Teaching LMMs for Image Quality Scoring and InterpretingarXiv:2503.09197v2 Announce Type: replace Abstract: Image quality scoring and interpreting are two fundamental components of Image Quality Assessment (IQA). The former quantifies image quality, while →25 Sept 2026Unraveling the cognitive patterns of Large Language Models through module communitiesarXiv:2508.18192v2 Announce Type: replace Abstract: Large Language Models (LLMs) have reshaped our world with significant advancements in science, engineering, and society through applications ranging→25 Sept 2026Tag-Aware Structured Text Translation: Towards a Systematic UnderstandingarXiv:2609.29131v1 Announce Type: cross Abstract: Internet texts are replete with format tags that carry structural, semantic, and functional meaning. Current large language model (LLM)-based translat→29 Sept 202650B+ MoEs with few active parameters, what's the sweet spot for intelligence, agent speed, and affordable fine-tuning?I’m building a Polish General purpose legal Model that drafts documents, answers questions using legal sources, and has enough coding ability to handle some automation. The workflow is very tool-heavy→5 Oct 2026Textualized and Feature-based Models for Compound Multimodal Emotion Recognition in the WildarXiv:2407.12927v4 Announce Type: replace Abstract: Systems for multimodal emotion recognition (ER) are commonly trained to extract features from different modalities (e.g., visual, audio, and textual
TechniqueMultimodal8 recent entries28 Aug 2026Graph-Guided Selective Unlearning for Language Models: Controlling Support Routes Beyond Forget SeedsarXiv:2608.26743v1 Announce Type: new Abstract: Enterprises fine-tune language models on proprietary data that may later require removal due to privacy, contractual, or compliance obligations. Selecti→4 Sept 2026KnowVis: Knowledge-Centric Visual Summarization for Video LecturesarXiv:2609.03742v1 Announce Type: cross Abstract: Video lectures are valuable educational resources, but their dense and lengthy formats often overwhelm novice learners. This difficulty stems from a f→11 Sept 2026Estimating Inconsistency Response Surfaces under Uncertainty in Cyber-Physical System DevelopmentarXiv:2609.11331v1 Announce Type: new Abstract: Cyber-Physical Systems (CPS) are commonly represented through multiple interconnected models. During development, CPS consistency requires that shared m→15 Sept 2026Q-SiT: Teaching LMMs for Image Quality Scoring and InterpretingarXiv:2503.09197v2 Announce Type: replace Abstract: Image quality scoring and interpreting are two fundamental components of Image Quality Assessment (IQA). The former quantifies image quality, while →17 Sept 2026Two weeks. That's how long it took to go from GLM-5.3-Flash's first run on domestic accelerators to serving all of its production traffic, w…Two weeks. That's how long it took to go from GLM-5.3-Flash's first run on domestic accelerators to serving all of its production traffic, with 3.2× end-to-end throughput along the way. What I keep th→5 Oct 2026Textualized and Feature-based Models for Compound Multimodal Emotion Recognition in the WildarXiv:2407.12927v4 Announce Type: replace Abstract: Systems for multimodal emotion recognition (ER) are commonly trained to extract features from different modalities (e.g., visual, audio, and textual→5 Oct 2026Causal discovery identifies pathways linking physical activity to dementia risk in the UK BioBankarXiv:2610.02221v1 Announce Type: cross Abstract: Physical Activity (PA) is consistently associated with lower risk of dementia, yet the mechanism linking PA to dementia prevention remain incomopletel→6 Oct 2026EgoExo-Next:Benchmarking Vision-Language Models on Visual-Option Next-State and Cross-View ReasoningarXiv:2610.04506v1 Announce Type: new Abstract: Vision-language models (VLMs) are increasingly evaluated for egocentric and cross-view video reasoning, yet existing benchmarks largely focus on semanti
TechniqueSafety8 recent entries14 Sept 2026From Bench-to-Bedside: A Review of Clinical Trials in Drug Discovery and DevelopmentarXiv:2412.09378v4 Announce Type: replace-cross Abstract: Clinical trials bridge basic research and clinical application, serving as essential steps in drug development. This review examines clinical →15 Sept 2026AI Deployment Accountability Engineering: A Vision for Accountable AI in Safety-Critical Socio-Technical SystemsarXiv:2609.14592v1 Announce Type: new Abstract: Artificial intelligence systems are rapidly becoming critical components in healthcare, finance, public services, and other safety-critical domains. Yet→23 Sept 2026Trustworthy Agentic AI: Failure Modes, Mitigation Strategies, and a Lifecycle Framework for Autonomous LLM SystemsarXiv:2609.22712v1 Announce Type: new Abstract: Agentic AI systems built on large language models can plan over multiple steps, use external tools, retain information in memory, and coordinate with ot→23 Sept 2026Control Barrier Functions for Safe Free-Flying Robotic Spacecraft Operations in Tumbling Target CapturearXiv:2609.25905v1 Announce Type: new Abstract: This paper presents a modular control barrier function (CBF) framework for safe free-flying robotic spacecraft operations during tumbling target capture→24 Sept 2026'AI Is Turning Too Human': How Teenagers Experience and Negotiate AI in Everyday LifearXiv:2609.27824v1 Announce Type: new Abstract: Generative AI is rapidly entering adolescents' everyday lives during a critical period of cognitive, social and emotional development. Yet its adoption →25 Sept 2026Tag-Aware Structured Text Translation: Towards a Systematic UnderstandingarXiv:2609.29131v1 Announce Type: cross Abstract: Internet texts are replete with format tags that carry structural, semantic, and functional meaning. Current large language model (LLM)-based translat→29 Sept 2026Q-learning Penalized Transformer for Safe Offline Reinforcement LearningarXiv:2609.34426v1 Announce Type: new Abstract: This paper addresses the problem of safe offline reinforcement learning, which involves training a policy to satisfy safety constraints using an offline→5 Oct 2026ULTRADISCOVERY: Abductive Exploration in an Interconnected, Epistemically Open UniversearXiv:2610.03092v1 Announce Type: cross Abstract: Scientific discovery often begins when scattered clues call for a new way of describing the world. Such abductive exploration can require constructing