TechniqueRLHF / Alignment8 recent entries30 Sept 2026AutoMark: Enabling Autoresearch to Discover Better LLM WatermarksarXiv:2609.37310v1 Announce Type: cross Abstract: With LLM watermarking being deployed commercially and now required by regulations, improving its reliability and effectiveness has become crucial. Yet→1 Oct 2026Safety of Latent Communication in Multi-Agent SystemsarXiv:2609.39788v1 Announce Type: new Abstract: Latent communication enables multi-agent systems to exchange information directly in internal representation space, reducing the token, computation, and
TechniqueRAG6 recent entries13 May 2026[AINews] The End of FinetuningThis article likely discusses how advances in large language models, prompt engineering, and in-context learning are making traditional finetuning less necessary for many applications. It probably exp→19 May 2026CLAP: Contrastive Latent-space Prompt Optimization for End-to-end Autonomous DrivingarXiv:2605.17284v1 Announce Type: cross Abstract: End-to-end autonomous driving systems powered by Vision-Language-Action (VLA) models achieve strong performance on common driving scenarios, yet remai→1 Jun 2026Latent Geometric Chords for Query-Efficient Decision-Based Adversarial AttacksarXiv:2605.31219v1 Announce Type: new Abstract: While decision-based black-box adversarial attacks present a severe security threat, current methodologies suffer from fundamental limitations. Pixel-wi→1 Jun 2026ElasticMem: Latent Memory as a Learnable Resource for LLM AgentsarXiv:2605.30690v1 Announce Type: new Abstract: Long-term memory is essential for LLM agents to reason coherently across extended interactions, personalize responses, and reuse past experience. Howeve→10 Jun 2026One Token per Multimodal Evidence: Latent Memory for Resource-Constrained QAarXiv:2606.10572v1 Announce Type: new Abstract: External memory effectively grounds large language models (LLMs) and vision-language models (VLMs)-based question answering (QA) in relevant multimodal →10 Sept 2026BIO-MEMART: Biometric-Aware KV Cache Memory for Multi-User LLM AgentsarXiv:2609.08566v1 Announce Type: new Abstract: KV cache is evolving from a serving optimization into an external memory substrate for long-term LLM agents. In a shared multi-user deployment, however,
TechniqueAgents8 recent entries30 Sept 2026Cooperative Multi-Agent Vision-Language-Action Models via Reinforced Fine TuningarXiv:2609.36588v1 Announce Type: cross Abstract: We study reinforcement learning (RL) methods for cooperative multi-agent Vision-Language-Action (VLA) models. This problem is challenging because VLAs→30 Sept 2026AutoMark: Enabling Autoresearch to Discover Better LLM WatermarksarXiv:2609.37310v1 Announce Type: cross Abstract: With LLM watermarking being deployed commercially and now required by regulations, improving its reliability and effectiveness has become crucial. Yet→1 Oct 2026Safety of Latent Communication in Multi-Agent SystemsarXiv:2609.39788v1 Announce Type: new Abstract: Latent communication enables multi-agent systems to exchange information directly in internal representation space, reducing the token, computation, and→1 Oct 2026Cycle-Aware Autoencoder with Cross-SignalConsistency for Railway Door Anomaly DetectionarXiv:2609.39035v1 Announce Type: cross Abstract: Passenger access doors are safety-critical subsystems in railway vehicles, yet detecting abnormal door behavior in real operation is challenging becau→9 Oct 2026LR-V2X: Loss-Resilient Collaborative Perception under Low-Bandwidth CommunicationarXiv:2610.11264v1 Announce Type: new Abstract: Given the inherent unpredictability of packet loss in vehicular wireless communications, V2X collaborative perception can yield practical benefits only →9 Oct 2026Fluid-Gen-Zero: Grounding Pretrained Video Generators in Physics without TrainingarXiv:2610.10984v1 Announce Type: new Abstract: We present Fluid-Gen-Zero, a training-free framework for physics-aware fluid-object interaction video generation that decouples physical reasoning from →9 Oct 2026Examining Social Attribution in LLM Reasoning: A Theory-Guided Probing MethodologyarXiv:2610.12022v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed in sociotechnical systems where social attribution, the reasoning process attributing external →12 Oct 2026How Anthropic’s Dynamic Workflows Coordinate Claude AgentsAt AI Engineer New York 2026, Anthropic introduced **dynamic workflows** (also called “flows”), a new type of multi‑agent orchestration designed for large, ambitious workloads using Claude Managed Age
TechniqueFine-tuning8 recent entries3 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. ⏱→7 Sept 2026Krea2 Turbo Distill 4 step LoRA - FINAL Version released todayKrea 2 Turbo — 4-Step Distillation LoRA Full details and to download - HF Repo: https://huggingface.co/lvladikov/Krea2-Turbo-Distill-4step-LoRA https://preview.redd.it/9p2rjwh3y3oh1.jpg?width=3072&for→15 Sept 2026Semantic Privacy Protection with Utility Preservation for 3D Point CloudsarXiv:2609.13823v1 Announce Type: new Abstract: Point cloud data face serious semantic privacy risks during acquisition, transmission, and cross-institutional sharing. Existing methods mostly rely on →30 Sept 2026Cooperative Multi-Agent Vision-Language-Action Models via Reinforced Fine TuningarXiv:2609.36588v1 Announce Type: cross Abstract: We study reinforcement learning (RL) methods for cooperative multi-agent Vision-Language-Action (VLA) models. This problem is challenging because VLAs→6 Oct 2026No Concept Escapes the Audit: Auditing-Aware Unlearning for Verifiable Concept Erasure in Diffusion ModelsarXiv:2610.05401v1 Announce Type: new Abstract: Text-to-image diffusion models can generate prohibited content, which motivates concept erasure through machine unlearning. Most erasure methods interve→6 Oct 2026EagleDepth: Efficient Fine-Grained Depth Estimation via Pixel Diffusion DecoderarXiv:2610.04554v1 Announce Type: new Abstract: Recovering detailed geometry from high-resolution images is critical for precise perception of the surroundings and objects. However, existing methods w→7 Oct 2026Atom-JEPA: Joint-Embedding Predictive Architecture for 3D Atomistic SystemsarXiv:2610.08400v1 Announce Type: cross Abstract: Large-scale self-supervised pretraining has reshaped modern machine learning, substantially advancing the ability of language and vision models to gen→8 Oct 2026Breaking Adversarial Transferability in Fine-Tuned Speech RecognitionarXiv:2610.09109v1 Announce Type: new Abstract: Many organizations fine-tune publicly available pretrained Automatic Speech Recognition (ASR) models and deploy them in black-box settings, assuming lim
TechniqueMultimodal8 recent entries29 Sept 2026Principal Steering Subspaces for Online Adaptation of Frozen Generative Robot PoliciesarXiv:2609.33765v1 Announce Type: new Abstract: Generative robot policies provide expressive behavior priors, but updating a large diffusion or flow-matching model through online interaction is costly→30 Sept 2026Disentangling Spurious Correlations in Vision-Language-Action Models via Predicting Domain-Invariant Latent LookaheadarXiv:2609.37165v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models remain brittle under visual distribution shifts, often relying on spurious correlations tied to domain-specific fact→30 Sept 2026Cooperative Multi-Agent Vision-Language-Action Models via Reinforced Fine TuningarXiv:2609.36588v1 Announce Type: cross Abstract: We study reinforcement learning (RL) methods for cooperative multi-agent Vision-Language-Action (VLA) models. This problem is challenging because VLAs→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→7 Oct 2026SAE++: Cascaded Sparse Autoencoders Learn Multi-Level Visual Concepts in Multimodal LLMsarXiv:2606.16193v2 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) have demonstrated strong performance on vision-language tasks, yet their internal visual representati→7 Oct 2026Atom-JEPA: Joint-Embedding Predictive Architecture for 3D Atomistic SystemsarXiv:2610.08400v1 Announce Type: cross Abstract: Large-scale self-supervised pretraining has reshaped modern machine learning, substantially advancing the ability of language and vision models to gen→8 Oct 2026Quantifying Volumetric Risk: Class-Aware Asymmetric Weighted Conformal Prediction for 3D Medical Image SegmentationarXiv:2610.09392v1 Announce Type: new Abstract: Reliable volumetric segmentation is critical for clinical diagnostics, yet foundation models such as MedSAM remain deterministic and lack calibrated unc→9 Oct 2026Fluid-Gen-Zero: Grounding Pretrained Video Generators in Physics without TrainingarXiv:2610.10984v1 Announce Type: new Abstract: We present Fluid-Gen-Zero, a training-free framework for physics-aware fluid-object interaction video generation that decouples physical reasoning from
TechniqueSafety8 recent entries1 Oct 2026Safety of Latent Communication in Multi-Agent SystemsarXiv:2609.39788v1 Announce Type: new Abstract: Latent communication enables multi-agent systems to exchange information directly in internal representation space, reducing the token, computation, and→1 Oct 2026Cycle-Aware Autoencoder with Cross-SignalConsistency for Railway Door Anomaly DetectionarXiv:2609.39035v1 Announce Type: cross Abstract: Passenger access doors are safety-critical subsystems in railway vehicles, yet detecting abnormal door behavior in real operation is challenging becau→2 Oct 2026Getting Out and Getting Back: World and Behavior Grounding in Real2Sim2Real Co-TrainingarXiv:2610.00821v1 Announce Type: new Abstract: Simulation can expand scarce real demonstrations for co-training, yet how world fidelity and similarity to human behavior affect policy performance rema→6 Oct 2026MGPO: Manifold-Guided Diffusion Alignment for Task-Aware Dataset DistillationarXiv:2610.05252v1 Announce Type: new Abstract: Diffusion-based dataset distillation (DD) suffers from a fundamental objective mismatch: likelihood-driven diffusion models prioritize density approxima→7 Oct 2026Modeling Latent Disturbances for Robust Decision-Making in World ModelsarXiv:2610.07599v1 Announce Type: cross Abstract: In this paper, we study robust decision-making in the latent space of world models (WMs). Robust optimization is a mathematical framework where, given→7 Oct 2026Latent space bias directions in LLMs capture confidence, not fairnessarXiv:2610.08559v1 Announce Type: cross Abstract: Activation steering has gained popularity as a lightweight inference-time debiasing technique for large language models. However, prior work reports t→8 Oct 2026LASER: Latent Space Adjoint Matching for Support-Constrained Entropy-Regularized Offline RLarXiv:2610.08989v1 Announce Type: new Abstract: While offline reinforcement learning (RL) enables policy optimization from static datasets without costly online interaction, it remains bottlenecked by→8 Oct 2026Breaking Adversarial Transferability in Fine-Tuned Speech RecognitionarXiv:2610.09109v1 Announce Type: new Abstract: Many organizations fine-tune publicly available pretrained Automatic Speech Recognition (ASR) models and deploy them in black-box settings, assuming lim