TechniqueRLHF / Alignment8 recent entries11 Apr 2026All ModelsAuto-generated index of all models mentioned across the wiki.→11 Apr 2026All CompaniesAuto-generated index of all companies mentioned across the wiki.→30 Apr 2026DenseStep2M: A Scalable, Training-Free Pipeline for Dense Instructional Video AnnotationarXiv:2604.26565v1 Announce Type: new Abstract: Long-term video understanding requires interpreting complex temporal events and reasoning over procedural activities. While instructional video corpora,
TechniqueRAG8 recent entries11 Apr 2026All PapersAuto-generated index of all papers mentioned across the wiki.→11 Apr 2026All ModelsAuto-generated index of all models mentioned across the wiki.→11 Apr 2026All CompaniesAuto-generated index of all companies mentioned across the wiki.→20 Apr 2026Mitigating hallucinations and omissions in LLMs for invertible problems: An application to hardware logic design automationarXiv:2512.03053v2 Announce Type: replace-cross Abstract: We show for invertible problems that transform data from a source domain (for example, Logic Condition Tables (LCTs)) to a destination domain →13 May 2026ClinicalBench: Stress-Testing Assertion-Aware Retrieval for Cross-Admission Clinical QA on MIMIC-IVarXiv:2605.11143v1 Announce Type: new Abstract: Reasoning benchmarks measure clinical performance on clean inputs. We evaluate the step before reasoning: retrieval over real EHR notes, where negation,→12 Sept 2026Natural Language Access to Domain-Specific Metadata: A Reusable Framework for LLM Query GenerationarXiv:2607.18029v2 Announce Type: replace-cross Abstract: Researchers need to answer ad-hoc questions about the contents of domain-specific archives but often lack the expertise to write structured qu→4 Oct 2026Synthesis: Arxiv-Cs-ClAuto-generated synthesis of 10865 entries about arxiv-cs-cl→4 Oct 2026Synthesis: Arxiv-Cs-AiAuto-generated synthesis of 29846 entries about arxiv-cs-ai
TechniqueAgents8 recent entries14 Aug 2026Training AI Scientists to Replicate ResearcharXiv:2608.13331v1 Announce Type: cross Abstract: The replicability of papers is a cornerstone of scientific knowledge, ensuring the reliability of existing results and providing a base for further ex→14 Aug 2026A 27B agent just beat Claude Opus 4.8 and GPT-5.5 on held-out research replication. Replica turns paper replication into a scalable RL task …A 27B agent just beat Claude Opus 4.8 and GPT-5.5 on held-out research replication. Replica turns paper replication into a scalable RL task space. Replicating a paper forces the same hypothesis-driven→27 Aug 2026Reimagining work: How Pythian’s internal AI playbook delivers customer ROIWhen Pythian rolled out Google Cloud’s Gemini Enterprise across our 500-person company in 27 countries, the goal was simple: use our own company as a proving ground to discover how enterprise AI actua→12 Sept 2026Natural Language Access to Domain-Specific Metadata: A Reusable Framework for LLM Query GenerationarXiv:2607.18029v2 Announce Type: replace-cross Abstract: Researchers need to answer ad-hoc questions about the contents of domain-specific archives but often lack the expertise to write structured qu→21 Sept 2026Great paper from Microsoft Research and colleagues. If you auto-generate MCP tools from agent trajectories, this one is worth your time. Aut…Great paper from Microsoft Research and colleagues. If you auto-generate MCP tools from agent trajectories, this one is worth your time. AutoTailor turns web trajectories into parameterized browser-au→4 Oct 2026Synthesis: TechmemeAuto-generated synthesis of 3157 entries about techmeme→4 Oct 2026Synthesis: Arxiv-Cs-ClAuto-generated synthesis of 10865 entries about arxiv-cs-cl→4 Oct 2026Great paper from Microsoft and colleagues on optimizing agent harnesses. Current harness optimizers change how the harness is updated but ke…Great paper from Microsoft and colleagues on optimizing agent harnesses. Current harness optimizers change how the harness is updated but keep the training scenarios fixed, so feedback keeps coming fr
TechniqueFine-tuning8 recent entries30 Apr 2026DenseStep2M: A Scalable, Training-Free Pipeline for Dense Instructional Video AnnotationarXiv:2604.26565v1 Announce Type: new Abstract: Long-term video understanding requires interpreting complex temporal events and reasoning over procedural activities. While instructional video corpora,→2 Jun 2026LEGS: Fine-Tuning Teleop-Free VLAs for Humanoid Loco-manipulation in an Embodied Gaussian Splatting WorldarXiv:2606.01458v1 Announce Type: new Abstract: Training vision-language-action (VLA) policies for humanoid loco-manipulation is constrained by the high cost and complexity of collecting human teleope→25 Jun 2026Optimizing Abstractive Summarization With Fine-Tuned PEGASUSarXiv:2606.25462v1 Announce Type: new Abstract: Abstractive text summarization is the technique of generating a short and concise summary comprising the salient ideas of a source text without making a→29 Jul 2026DocAnnot -- Accelerating the Creation of Key Information Extraction Datasets with GenAI-Powered Auto-annotationarXiv:2607.24745v1 Announce Type: cross Abstract: Key Information Extraction (KIE) is vital for many document applications, but creating training datasets is traditionally a time-consuming manual proc→3 Sept 2026Krea2 Turbo Distill 4 step LoRA - new checkpoint (chk60K) released (fine detail now above the 8-step teacher and clean of artefacts, best prompt-adherence and teacher-faithfulness scores so far)Krea 2 Turbo — 4-Step Distillation LoRA (work in progress) A LoRA for Krea 2 Turbo that reduces the minimum usable step count from 8 to 4. ⚡ Half the steps — 8 → 4, on Turbo's own deployment sigmas. ⏱→12 Sept 2026Natural Language Access to Domain-Specific Metadata: A Reusable Framework for LLM Query GenerationarXiv:2607.18029v2 Announce Type: replace-cross Abstract: Researchers need to answer ad-hoc questions about the contents of domain-specific archives but often lack the expertise to write structured qu→4 Oct 2026Synthesis: R-StablediffusionAuto-generated synthesis of 2154 entries about r-stablediffusion→4 Oct 2026Synthesis: Arxiv-Cs-ClAuto-generated synthesis of 10865 entries about arxiv-cs-cl
TechniqueMultimodal8 recent entries30 Apr 2026DenseStep2M: A Scalable, Training-Free Pipeline for Dense Instructional Video AnnotationarXiv:2604.26565v1 Announce Type: new Abstract: Long-term video understanding requires interpreting complex temporal events and reasoning over procedural activities. While instructional video corpora,→2 Jun 2026LEGS: Fine-Tuning Teleop-Free VLAs for Humanoid Loco-manipulation in an Embodied Gaussian Splatting WorldarXiv:2606.01458v1 Announce Type: new Abstract: Training vision-language-action (VLA) policies for humanoid loco-manipulation is constrained by the high cost and complexity of collecting human teleope→29 Jul 2026DocAnnot -- Accelerating the Creation of Key Information Extraction Datasets with GenAI-Powered Auto-annotationarXiv:2607.24745v1 Announce Type: cross Abstract: Key Information Extraction (KIE) is vital for many document applications, but creating training datasets is traditionally a time-consuming manual proc→3 Sept 2026Krea2 Turbo Distill 4 step LoRA - new checkpoint (chk60K) released (fine detail now above the 8-step teacher and clean of artefacts, best prompt-adherence and teacher-faithfulness scores so far)Krea 2 Turbo — 4-Step Distillation LoRA (work in progress) A LoRA for Krea 2 Turbo that reduces the minimum usable step count from 8 to 4. ⚡ Half the steps — 8 → 4, on Turbo's own deployment sigmas. ⏱→4 Oct 2026Synthesis: Arxiv-Cs-RoAuto-generated synthesis of 5773 entries about arxiv-cs-ro→4 Oct 2026Synthesis: Arxiv-Cs-CvAuto-generated synthesis of 18054 entries about arxiv-cs-cv→4 Oct 2026Synthesis: Arxiv-Cs-ClAuto-generated synthesis of 10865 entries about arxiv-cs-cl→4 Oct 2026Synthesis: Arxiv-Cs-AiAuto-generated synthesis of 29846 entries about arxiv-cs-ai
TechniqueSafety8 recent entries21 Apr 2026Arch: An AI-Native Hardware Description Language for Register-Transfer Clocked Hardware DesignarXiv:2604.05983v2 Announce Type: replace-cross Abstract: We present Arch (AI-native Register-transfer Clocked Hardware), a hardware description language for micro-architecture specification and AI-as→27 May 2026Completely agree, @hwchase17 ! This is the meta-level breakthrough we've all been waiting for. Self-optimizing loops finally feel production…Completely agree, @hwchase17 ! This is the meta-level breakthrough we've all been waiting for. Self-optimizing loops finally feel production-ready because LangSmith Engine turns evaluation from a manu→2 Jun 2026LEGS: Fine-Tuning Teleop-Free VLAs for Humanoid Loco-manipulation in an Embodied Gaussian Splatting WorldarXiv:2606.01458v1 Announce Type: new Abstract: Training vision-language-action (VLA) policies for humanoid loco-manipulation is constrained by the high cost and complexity of collecting human teleope→15 Jul 2026How to Analyze and Govern Gemini Enterprise App Usage at Scale with BigQueryDeploying the Gemini Enterprise app across an organization marks a transformative leap forward in workforce productivity, providing employees with an amazing, high-performance suite of agentic AI tool→4 Sept 2026Two-Stage Reinforcement Learning for Sound and Adversarial Test Generation in Code LLMsarXiv:2609.03955v1 Announce Type: new Abstract: Reinforcement learning (RL) has substantially advanced code generation with large language models (LLMs) through executable feedback. The feedback for c→4 Oct 2026Synthesis: Gary-Marcus--XAuto-generated synthesis of 2011 entries about gary-marcus--x→4 Oct 2026Synthesis: Arxiv-Cs-RoAuto-generated synthesis of 5773 entries about arxiv-cs-ro→4 Oct 2026Synthesis: Arxiv-Cs-ClAuto-generated synthesis of 10865 entries about arxiv-cs-cl