TechniqueRLHF / Alignment8 recent entries12 Oct 2026Grounded-Dreamer: Robot Learning from World Model Synthetic Data with Physical GroundingarXiv:2610.13164v1 Announce Type: new Abstract: Scaling robot manipulation policies requires large amounts of diverse, action-labeled data, yet collecting such data in the real world remains expensive→12 Oct 2026EmoGavel: Grounding-Aware Reinforcement Learning with Verifiable Rewards for Multimodal Emotion Preference LearningarXiv:2610.13353v1 Announce Type: cross Abstract: Multimodal emotion preference learning uses pairwise comparisons to identify which open-ended emotion descriptions align more closely with human judgm
TechniqueRAG8 recent entries8 Oct 2026New challenge: consolidated 2 cards in a single system but one card hogs all the models even if I run 2 different instances of Ollama on 2 different portsIn my attempt to combat powerty; as electricity cost a ton these days and it is hot as hell, I consolidated 2 machines into one, so my 2 crappy machines now are one, and that means a bit less power an→8 Oct 2026Beyond Outcome Rewards: Constructing and Assigning Retrieval Credit for Search AgentsarXiv:2610.10179v1 Announce Type: new Abstract: Search agents enable Large Language Models (LLMs) to iteratively retrieve and use information for complex multi-hop questions. Reinforcement Learning wi→9 Oct 2026DaCe-DT: Data-Centric Offline Multi-Task Reinforcement Learning via Adaptive Prompts and Trajectory Correction for Heterogeneous TasksarXiv:2610.11085v1 Announce Type: new Abstract: Offline multi-task reinforcement learning (Offline MTRL) heavily depends on the quality and distribution of pre-collected data. However, existing method→12 Oct 2026Verifiable Retrieval for Legal Reasoning through Structure-driven Knowledge GrapharXiv:2610.13695v1 Announce Type: new Abstract: Any automation within reliability-critical contexts such as medicine or law has to be transparent and verifiable. Despite their advantages, current LLM-→12 Oct 2026Towards Enriching Design-Time Models with Evidence from Simulation and Operational ActivitiesarXiv:2610.13456v1 Announce Type: new Abstract: Cyber-Physical Systems are developed through multiple model based activities, comprising several stages of development. As the development progresses th→12 Oct 2026Must-read paper on the effectiveness of multi-agent systems and persistent memory. We have recently seen many viral examples of multi-agent …Must-read paper on the effectiveness of multi-agent systems and persistent memory. We have recently seen many viral examples of multi-agent systems scaled via persistent memory. This work takes a clos→12 Oct 2026Can Language Models Play the Wikipedia Game?arXiv:2610.13948v1 Announce Type: new Abstract: Language models increasingly support or automate information retrieval from document collections too large to index. This task is difficult when it requ→12 Oct 2026A 'free' multi-modal 'embedding' model (already) included with your LLM: vLLM plugin + upstream PRDisclaimer: I work for NuMind, the company behind this plugin. TLDR: Text/image (simili-)embeddings from the LLM you already have loaded :-) I've been working on making it easier to obtain embeddings
TechniqueAgents8 recent entries12 Oct 2026Hyper Algorithm Design Agent: Evolving Learnable Optimizer from ZeroarXiv:2609.35328v2 Announce Type: replace Abstract: Meta-Black-Box Optimization (MetaBBO) is one of the highlights in the recent AI for Optimization trend. This paradigm's bi-level workflow leverages →12 Oct 2026Does Learning Recurrent Networks Matter in Partially Observable RL?arXiv:2610.13197v1 Announce Type: cross Abstract: Reinforcement learning (RL) under partial observability typically re- lies on recurrent networks to encode temporal information, with the recurrent mo→12 Oct 2026Does Knowledge About Perceptual Uncertainty Help an Agent in Automated Driving?arXiv:2502.11864v2 Announce Type: replace-cross Abstract: Agents in real-world scenarios like automated driving deal with uncertainty in their environment, in particular due to perceptual uncertainty.→12 Oct 2026Data-Driven Stochastic Optimal Control in Reproducing Kernel Hilbert SpacesarXiv:2407.16407v3 Announce Type: replace-cross Abstract: This paper proposes a fully data-driven approach for optimal control of nonlinear control-affine systems represented by a stochastic diffusion→12 Oct 2026Can Failed Trajectories Reveal Where Agents Go Wrong? Agentic Failure Attribution Without Step-Level LabelsarXiv:2610.13105v1 Announce Type: new Abstract: Failure attribution for LLM agents aims to identify decisive steps responsible for task failure, which is critical for debugging and improving agentic s→12 Oct 2026Byzantine-Resilient Federated Large Language Model via Hypergraph Message PassingarXiv:2610.12711v1 Announce Type: new Abstract: Federated Large Language Models (FedLLMs) are promising to deliver privacy-preserving, collaborative intelligence. The decentralized training process is→12 Oct 2026A Multi-Agent LLM System for Automated Tuning of Specialized Neural Network ModelsarXiv:2610.13663v1 Announce Type: new Abstract: Many machine learning approaches are two-level: an expert selects a class of methods, within this class the choice of key components is critical and usu→13 Oct 2026Banger paper from Google DeepMind on co-evolving an agent's harness and its weights. (bookmark it) If you already log your harness changes a…Banger paper from Google DeepMind on co-evolving an agent's harness and its weights. (bookmark it) If you already log your harness changes and results, those logs can become training data for the mode
TechniqueFine-tuning8 recent entries12 Oct 2026Kernelized Parameter Sensitivity Atlases for Amortized Conditional InterpretabilityarXiv:2610.12737v1 Announce Type: new Abstract: Gradient-based attribution provides input-specific information about model parameters, but computing it via backpropagation for many samples is expensiv→12 Oct 2026Introducing DigitalOcean Signals and Simulations: see how your agents and models really behave in production, then test the fix before it shipsYou ship an agent. It mostly works. Then the feedback loop becomes a support ticket: a user got the wrong answer, a tool call looped four times, a refund went out that shouldn’t have. Standard observa→12 Oct 2026epGen: open LoRA for LTX-2.5 that gives every sound in the video its own audio track (generation + separation, weights on HF)LTX-2.5 makes a video with one mixed soundtrack. Our LoRA also outputs one track per captioned sound, in the same run. Prompt 'a jeep, its engine growling' and 'a taxi, its horn honking' and you get t→12 Oct 2026EmoGavel: Grounding-Aware Reinforcement Learning with Verifiable Rewards for Multimodal Emotion Preference LearningarXiv:2610.13353v1 Announce Type: cross Abstract: Multimodal emotion preference learning uses pairwise comparisons to identify which open-ended emotion descriptions align more closely with human judgm→12 Oct 2026Byzantine-Resilient Federated Large Language Model via Hypergraph Message PassingarXiv:2610.12711v1 Announce Type: new Abstract: Federated Large Language Models (FedLLMs) are promising to deliver privacy-preserving, collaborative intelligence. The decentralized training process is→12 Oct 2026Auditing Prompt Injection Defenses Before They Reach Users: What Strong Adversaries RevealarXiv:2505.15738v3 Announce Type: replace-cross Abstract: Large language models are increasingly deployed in user-facing products that handle sensitive personal data while interacting with untrusted e→12 Oct 2026A hyper realism Krea2 model generate Magazine page with multiple photos in one shot -I’ve wanted this for a long time: a Krea-2 model that gives you a magazine page in one shot. Flash-lit gravure sets, film grain, multi-photo layouts on white paper, big headlines, covers and back cove→12 Oct 2026A Categorical Atlas of Parameter-Efficient Fine-Tuning: Cones, Orbits, and GaugesarXiv:2610.12728v1 Announce Type: new Abstract: Parameter-efficient fine-tuning has hundreds of methods, usually compared by parameter count and benchmark score. We compare them as maps. A pretrained
TechniqueMultimodal8 recent entries12 Oct 2026MotionCoach: Constructing Multimodal Guidance for Video Professional Motion EditingarXiv:2610.12963v1 Announce Type: cross Abstract: Video editing models achieve strong performance in modifying appearance, backgrounds, styles, and motions, empowered by large-scale training data. Bey→12 Oct 2026EmoGavel: Grounding-Aware Reinforcement Learning with Verifiable Rewards for Multimodal Emotion Preference LearningarXiv:2610.13353v1 Announce Type: cross Abstract: Multimodal emotion preference learning uses pairwise comparisons to identify which open-ended emotion descriptions align more closely with human judgm→12 Oct 2026Efficient Audio-Visual Speech Enhancement via Reinforcement Learning-Based Neural Architecture SearcharXiv:2610.12796v1 Announce Type: cross Abstract: Audio-visual speech enhancement (AVSE) improves speech intelligibility in noisy environments but often relies on computationally expensive models unsu→12 Oct 2026CORE-Seg: Reasoning-Driven Segmentation for Complex Lesions via Reinforcement LearningarXiv:2603.05911v2 Announce Type: replace-cross Abstract: Medical image segmentation is undergoing a paradigm shift from conventional visual pattern matching to cognitive reasoning analysis. Although →12 Oct 2026Can Language Models Play the Wikipedia Game?arXiv:2610.13948v1 Announce Type: new Abstract: Language models increasingly support or automate information retrieval from document collections too large to index. This task is difficult when it requ→12 Oct 2026Auditing Prompt Injection Defenses Before They Reach Users: What Strong Adversaries RevealarXiv:2505.15738v3 Announce Type: replace-cross Abstract: Large language models are increasingly deployed in user-facing products that handle sensitive personal data while interacting with untrusted e→12 Oct 2026A Multi-Agent LLM System for Automated Tuning of Specialized Neural Network ModelsarXiv:2610.13663v1 Announce Type: new Abstract: Many machine learning approaches are two-level: an expert selects a class of methods, within this class the choice of key components is critical and usu→12 Oct 2026A 'free' multi-modal 'embedding' model (already) included with your LLM: vLLM plugin + upstream PRDisclaimer: I work for NuMind, the company behind this plugin. TLDR: Text/image (simili-)embeddings from the LLM you already have loaded :-) I've been working on making it easier to obtain embeddings
TechniqueSafety8 recent entries12 Oct 2026Recommended NVIDIA paper on memory-efficient post-training RL. A very interesting technique for scaling RL for LLMs. The main takeaway is th…Recommended NVIDIA paper on memory-efficient post-training RL. A very interesting technique for scaling RL for LLMs. The main takeaway is that you can update all of a model's weights with RL and still→12 Oct 2026MotionCoach: Constructing Multimodal Guidance for Video Professional Motion EditingarXiv:2610.12963v1 Announce Type: cross Abstract: Video editing models achieve strong performance in modifying appearance, backgrounds, styles, and motions, empowered by large-scale training data. Bey→12 Oct 2026L_0 Feature Selection via Monte Carlo Tree Search in High-Dimensional Financial RegressionarXiv:2610.13574v1 Announce Type: new Abstract: Feature selection is a central problem in high-dimensional financial regression, where large numbers of engineered variables and strong correlations amo→12 Oct 2026Introducing RSI-Anything: Unlocking Recursive Self-Improvement with World Models 🚀 Can AI learn to improve itself by predicting the consequ…Introducing RSI-Anything: Unlocking Recursive Self-Improvement with World Models 🚀 Can AI learn to improve itself by predicting the consequences of its actions? Built on JEPA-Anything, RSI-Anything us→12 Oct 2026Hyper Algorithm Design Agent: Evolving Learnable Optimizer from ZeroarXiv:2609.35328v2 Announce Type: replace Abstract: Meta-Black-Box Optimization (MetaBBO) is one of the highlights in the recent AI for Optimization trend. This paradigm's bi-level workflow leverages →12 Oct 2026Grounded-Dreamer: Robot Learning from World Model Synthetic Data with Physical GroundingarXiv:2610.13164v1 Announce Type: new Abstract: Scaling robot manipulation policies requires large amounts of diverse, action-labeled data, yet collecting such data in the real world remains expensive→12 Oct 2026Goal-Oriented Bundle Management and Flow Control for Deep-Space Communications via Reinforcement LearningarXiv:2610.13923v1 Announce Type: cross Abstract: Deep-space communications operate under intermittent connectivity, long propagation delays, and relay storage constraints. In such networks, the Bundl→12 Oct 2026CASTER: Formalizing Zero-Shot Manipulation from Synthetic Videos as Constrained OptimizationarXiv:2610.12567v1 Announce Type: new Abstract: Prior research on learning from humans often requires real human demonstrations. But advances in video generation models offer a new paradigm: we can no