TechniqueRLHF / Alignment7 recent entries12 May 2026Concordia: Self-Improving Synthetic Tables for Federated LLMsarXiv:2605.09855v1 Announce Type: new Abstract: Federated learning (FL) enables training large language models (LLMs) without sharing raw data, but adapting LLMs under strict data isolation and non-II→10 Jun 2026Bittensor Agent Arenas as a Trajectory Primitive: Distilling a Shopping Agent from ShoppingBench Subnet TracesarXiv:2606.10064v1 Announce Type: cross Abstract: Small-model agentic post-training is bottlenecked less by the algorithm than by the trajectory substrate it consumes. Leading recipes (RLVR, group-rel
TechniqueAgents8 recent entries25 Jun 2026New research from Meta. Building synthetic training data has stayed a fixed pipeline that you hand-tune and then freeze. Autodata casts an A…New research from Meta. Building synthetic training data has stayed a fixed pipeline that you hand-tune and then freeze. Autodata casts an AI agent as a data scientist that builds training and evaluat→23 Jul 2026Environment-free Synthetic Data Generation for API-Calling AgentsApple ML shows LLM world-model simulation can generate API-agent training trajectories from specs alone—no executable environments required.→28 Jul 2026Real2Sim2Real for Vision-Language-Action Manipulation: An AMD ROCm-Based PipelinearXiv:2607.22997v1 Announce Type: cross Abstract: Physical AI -- the integration of large vision-language-action (VLA) models with embodied agents that act in the real world -- has emerged as the next→12 Aug 2026We are in an insane run of open-weight drops. Every modality, open source is winning. This is what an open source AI summer ☀️ looks like: …We are in an insane run of open-weight drops. Every modality, open source is winning. This is what an open source AI summer ☀️ looks like: 🧠 LLMs & Reasoning → DeepSeek-V4-Flash-0731 (my king 👑): 304B→7 Sept 2026// Evaluating and Improving LLM Self-Modeling // Really interesting paper. Can a model answer questions about its own behavior? The question…// Evaluating and Improving LLM Self-Modeling // Really interesting paper. Can a model answer questions about its own behavior? The questions are deliberately verifiable, such as whether a particular →11 Sept 2026When Synthetic Data Hurts: On Catastrophic Forgetting in Skill Retrieval for LLM AgentsarXiv:2609.10750v1 Announce Type: cross Abstract: LLM agents increasingly rely on external skills retrieved at runtime, making skill selection from large repositories a critical challenge. We present →5 Oct 2026PaMIR: Open Benchmark of Public Credit-Default DatasetsarXiv:2610.03259v1 Announce Type: new Abstract: We release PaMIR (Public Arrival-ordered Measurement for Inference in Risk), an open benchmark for credit-default prediction when labels are scarce and →9 Oct 2026SynCo: Data Synthesis Co-Training for Self-Evolving LLMs via Multi-Agent Reinforcement LearningarXiv:2610.11345v1 Announce Type: new Abstract: Self-evolving LLM agents promise to improve autonomously through continual interaction and learning, reducing their dependence on manually curated super
TechniqueFine-tuning8 recent entries27 Aug 2026Unfolding Scientific Papers into Multi-Turn Generation Trajectories for Continued Pre-TrainingarXiv:2608.25826v1 Announce Type: new Abstract: A recent line of synthetic-data work reconstructs the thinking behind existing text rather than rewriting the text itself, but it operates on short web →27 Aug 2026Mitigating LLM sycophancy with RL-based fine-tuning: Bayesian Truth Serum approacharXiv:2608.25267v1 Announce Type: new Abstract: Large language models (LLMs) frequently exhibit sycophancy: they adapt their answers to a user's stated beliefs or preferences instead of reporting what→28 Aug 2026FastVideo FastH3 V1: Open source 4-step Sparse Distilled H3 checkpoint/LORAHey guys, FastVideo team here. We saw how important speed and quality is for everyone. And we've been working to create our own step distill checkpoints and LORAs for MINIMAX h3. Here's is our v1 rele→11 Sept 2026When Synthetic Data Hurts: On Catastrophic Forgetting in Skill Retrieval for LLM AgentsarXiv:2609.10750v1 Announce Type: cross Abstract: LLM agents increasingly rely on external skills retrieved at runtime, making skill selection from large repositories a critical challenge. We present →17 Sept 2026When Audit Quality Fails to Predict Downstream Utility: A Counterfactual Study of Synthetic-Data Selectors for Low-Resource African NLParXiv:2609.18960v1 Announce Type: new Abstract: Quality-aware synthetic-data selection rests on a proxy: examples that an LLM judge rates as good should also help a downstream model learn. In a contro→25 Sept 2026Let Training Guide Selection: Online Synthetic Data Filtering via Real-Anchored UtilityarXiv:2609.29988v1 Announce Type: new Abstract: Synthetic data can scale training supervision when real-world data are limited, but noise and distribution mismatch can reduce its value. Existing synth→1 Oct 2026Comparison of techniques for fine-tuning open-weight models for entity extraction from radiology reportsarXiv:2609.40236v1 Announce Type: new Abstract: Converting free-text radiology reports into structured labels supports cohort building, quality assurance, and monitoring of clinical imaging models, bu→2 Oct 2026Training-Aware Target Coverage for Synthetic Data SelectionarXiv:2610.00814v1 Announce Type: cross Abstract: Synthetic data are increasingly used to scale LLM training, yet more synthetic data do not necessarily produce better models. Useful synthetic data mu
TechniqueMultimodal7 recent entries28 Jul 2026Real2Sim2Real for Vision-Language-Action Manipulation: An AMD ROCm-Based PipelinearXiv:2607.22997v1 Announce Type: cross Abstract: Physical AI -- the integration of large vision-language-action (VLA) models with embodied agents that act in the real world -- has emerged as the next→4 Aug 2026Entity-Faithful Repair of Synthetic Supervision for Zero-Shot Image CaptioningarXiv:2608.00994v1 Announce Type: cross Abstract: Zero-shot image captioning aims to generate image descriptions without annotated image-text pairs. Recent approaches exploit text-to-image models to s→12 Aug 2026We are in an insane run of open-weight drops. Every modality, open source is winning. This is what an open source AI summer ☀️ looks like: …We are in an insane run of open-weight drops. Every modality, open source is winning. This is what an open source AI summer ☀️ looks like: 🧠 LLMs & Reasoning → DeepSeek-V4-Flash-0731 (my king 👑): 304B→19 Aug 2026The 10th AI City ChallengearXiv:2608.17044v1 Announce Type: cross Abstract: The 10th AI City Challenge, held with ECCV 2026, marks a decade of community benchmarking for intelligent transportation, smart cities, and physical A→4 Sept 2026Building Pretraining Data for World Models: An Unreal Engine-Based Pipeline for Action-Conditioned Video GenerationarXiv:2609.03557v1 Announce Type: new Abstract: Action-conditioned video models require large-scale visual data paired with control signals that are temporally aligned with the resulting scene transit→28 Sept 2026AxonSynth: Domain-Randomized Synthetic Data for Zero-Shot 3D Axon Segmentation in Light-Sheet MicroscopyarXiv:2609.31431v1 Announce Type: new Abstract: Accurate segmentation of axons in 3D microscopy data is important for analyzing white-matter organization, but dense ground truth labels are expensive t→5 Oct 2026PaMIR: Open Benchmark of Public Credit-Default DatasetsarXiv:2610.03259v1 Announce Type: new Abstract: We release PaMIR (Public Arrival-ordered Measurement for Inference in Risk), an open benchmark for credit-default prediction when labels are scarce and
TechniqueSafety8 recent entries2 Jul 2026A Filtered Mixture-of-Generators for Fully Synthetic Survival TrainingarXiv:2607.00127v1 Announce Type: new Abstract: Survival analysis models time-to-event data, but in clinical settings training data are costly and scarce: events accrue over years of follow-up, cohort→3 Jul 2026When Sample Selection Bias Precipitates Model CollapsearXiv:2606.13732v2 Announce Type: replace Abstract: The proliferation of recursive training on synthetic data can alleviate data scarcity but risks model collapse, where repeated training erodes distr→12 Aug 2026We are in an insane run of open-weight drops. Every modality, open source is winning. This is what an open source AI summer ☀️ looks like: …We are in an insane run of open-weight drops. Every modality, open source is winning. This is what an open source AI summer ☀️ looks like: 🧠 LLMs & Reasoning → DeepSeek-V4-Flash-0731 (my king 👑): 304B→19 Aug 2026The 10th AI City ChallengearXiv:2608.17044v1 Announce Type: cross Abstract: The 10th AI City Challenge, held with ECCV 2026, marks a decade of community benchmarking for intelligent transportation, smart cities, and physical A→28 Sept 2026AxonSynth: Domain-Randomized Synthetic Data for Zero-Shot 3D Axon Segmentation in Light-Sheet MicroscopyarXiv:2609.31431v1 Announce Type: new Abstract: Accurate segmentation of axons in 3D microscopy data is important for analyzing white-matter organization, but dense ground truth labels are expensive t→29 Sept 2026Synthetic Thermal Image Generation for Real-Time Animal Detection Under Low-Visibility ConditionsarXiv:2609.32944v1 Announce Type: new Abstract: Wildlife-vehicle collisions remain a significant road safety concern, particularly during nighttime and low-visibility conditions when RGB-based percept→29 Sept 2026MaD-RL: Matching Distributions for Calibrating LLMs with Reinforcement LearningarXiv:2609.31644v1 Announce Type: new Abstract: Reinforcement learning (RL) is widely used in language-model post-training to maximize rewards assigned to individual model outputs, such as scores from→9 Oct 2026SynCo: Data Synthesis Co-Training for Self-Evolving LLMs via Multi-Agent Reinforcement LearningarXiv:2610.11345v1 Announce Type: new Abstract: Self-evolving LLM agents promise to improve autonomously through continual interaction and learning, reducing their dependence on manually curated super