ZeroHour
DashboardNewsCVEsExploitsIncidentsAIBriefAnalyticsEntitiesWatchlistIOCsAsk the feedSourcesFeeds & APIKiosk mode

Search: “deployment”

18 stories in the last 3d

Searchkeywordsmart Sortlatesthotimportancerelevance
DomainAllCyberAIWindow24h3d7d30dAllIn the wildImportant onlyShow duplicates
CategoryAllAI safety & security 40Vulnerability 36Exploit / PoC 32Threat actor 24Industry 22Advisory 21AI research 19AI industry 18Malware 17Model release 12Research 11Tools 9Data breach 6Ransomware 6
SeverityAllcritical 19high 77medium 56low 2info 135

Workspace Models: Lightweight Robotic Memory via Saliency-Driven Supervision

Researchers propose workspace tokens, a lightweight latent robot memory distilled from train-time VLM saliency queries, improving policy performance without in-loop VLM calls.

The paper introduces workspace tokens, a latent memory representation for robotic manipulation policies trained by using a VLM to identify task-relevant current and historical information and distilling it via a set-reconstruction decoder loss. At deployment the workspace token serves as a drop-in replacement for observations, letting policies solve memory-intensive tasks without expensive in-the-loop VLM queries. Experiments in simulation and on hardware show it is both more lightweight and yields better policy performance than conditioning on full histories or in-loop VLM compression.

arXiv cs.AI / cs.LG / cs.CL · 20h agoAI research

Prediction-Powered Smoothing and Validation for Disaggregated AI Evaluation

Researchers propose prediction-powered smoothing (PP-S/PP-TS), Bayesian small-area estimators that improve disaggregated AI evaluation accuracy and validation.

The paper treats AI evaluation sets as finite populations and improves domain-level mean estimates by combining prediction-powered inference with small area estimation. PP-S fits a Bayesian model to each domain's prediction-powered estimate, while PP-TS borrows strength across a reporting taxonomy. A new approximately unbiased design-based cross-validation score selects between direct and smoothed estimators, delivering better point and interval estimates with near-nominal coverage on a curated benchmark and human-graded deployed agent traffic.

arXiv cs.AI / cs.LG / cs.CL · 20h agoAI research

Accelerating Sharded Data Parallelism at Scale with Federated Learning

Hybrid FL+FSDP and FL+HSDP algorithms cut communication overhead in sharded data parallelism, accelerating Llama3.1 8B pre-training on 512 A100 GPUs by up to 8x.

The paper introduces FL+FSDP and FL+HSDP, hybrid algorithms that interleave sharded data parallelism with FedAvg-style federated aggregations to decouple large DP deployments into loosely-coupled federation groups. Formal communication-cost analysis and experiments on multi-tier GPU interconnects demonstrate scalability and flexibility. A Llama3.1 8B pre-training run on 512 A100 GPUs achieves up to 8.04x faster data processing and 4.48 lower evaluation perplexity than sharded DP baselines under identical hyperparameters.

arXiv cs.AI / cs.LG / cs.CL · 1d agoAI research

In-Context Robot Learning with VLM Agents

GPT-Policy uses commercial VLM agents like GPT-6 Astra for in-context robot learning, translating demonstrations and feedback into verified robot actions without gradient updates.

The paper (arXiv 2609.19138) presents GPT-Policy, a framework combining a context compiler that preserves task-relevant visual transitions, a VLM such as GPT-6 Astra that proposes robot-tool actions, and a constrained controller that verifies and executes each action. Real-robot trials show human video demonstrations improve task completion even without robot action labels, while aligned action references yield further gains on contact-sensitive tasks. Evaluation covers success and efficiency metrics, matched model comparisons, and controlled context ablations.

Hugging Face daily papers · 2d agoAI research1

Agile-WAM: An Agile Tactile World Action Model for Contact-Rich Robot Control

Researchers introduce Agile-WAM, a tactile world action model using direct vision-tactile-to-action flow matching for agile contact-rich robot control.

Agile-WAM encodes visual and tactile observations into a shared latent and jointly generates action chunks plus future visual and tactile latents via flow matching, avoiding large pretrained generative backbones. Multi-horizon multimodal prediction supervises visual latents at longer offsets while capturing abrupt tactile contact dynamics in the next frame. Across nine simulated and five real-world manipulation tasks it achieved a 29.4% relative success-rate gain over the strongest baseline with 11.9 ms inference latency.

arXiv cs.AI / cs.LG / cs.CL · 20h agoAI research

OPTED: On-Policy Fine-Tuning for End-to-End Driving using a Render-Free Teacher

OPTED decouples RL teacher training from closed-loop student post-training for end-to-end driving, raising TransFuser and VaVAM driving scores 1.6x and 9.5x.

OPTED trains a privileged teacher with reinforcement learning on vectorized HD-map and bounding-box inputs, then uses it to supervise pre-trained camera-based students during closed-loop post-training without costly sensor simulation. Applied to TransFuser and VaVAM in AlpaSim using 3DGS neural reconstructions of real driving logs, driving scores increased 1.6x and 9.5x respectively. In controlled experiments it matched direct RL post-training performance with roughly three orders of magnitude fewer simulator interactions.

arXiv cs.AI / cs.LG / cs.CL · 20h agoAI research

RAFT: A Stateful Retrieval-Augmented Framework for Troubleshooting Agents

Researchers introduce RAFT, a stateful retrieval-augmented framework that retrieves timeline entries from historical cases to improve enterprise troubleshooting agents.

RAFT abstracts closed support cases into directed chains of timeline entries and retrieves at the entry level, returning parent-case trajectories anchored at matched states, with an optional case-level similarity graph. It beat vanilla RAG and GraphRAG baselines on Case Hit at every stage of case progress, using a synthetic benchmark built from Microsoft Learn Windows Server documentation and real Apache Jira issues with human-created duplicate labels. The benchmark, implementation, and Jira evaluation set are publicly released.

arXiv cs.AI / cs.LG / cs.CL · 20h agoAI research

MILER: Semantic Mid-Level Representation for Sim-to-Real Reinforcement Learning in Unstructured Autonomous Driving

MILER achieves zero-shot sim-to-real reinforcement learning for autonomous driving, completing 17.3 km on a test track without human intervention.

MILER is an end-to-end reinforcement learning policy framework with zero-shot sim-to-real transfer for unstructured autonomous driving. It trains on a custom semantic mid-level representation simulator and uses BEVFusion to convert camera and LiDAR data into a matching semantic bird's-eye-view representation at deployment, with trajectory alignment replacing direct action application. The system drove 17.3 km with two vehicles on a 3.0 km test track at up to 33.6 km/h without intervention, running entirely on a Jetson AGX Orin.

arXiv cs.AI / cs.LG / cs.CL · 20h agoAI research

Deep Noir: Autonomous Steering Discovery via Architectural Chronometry in Transformer Models

Deep Noir automates activation steering parameter discovery and finds steering creates a prompt-injection attack surface that widens with steering magnitude.

Deep Noir uses Logit Lens convergence and causal head-level attribution to automatically discover where and how strongly to steer LLMs at inference time. Across nine models spanning 1B to 9B parameters and four architectures, it achieved gains of 21 to 42 percentage points on spam classification and 13.1 points on SST-2 sentiment, outperforming RepE without head masking. The paper also shows steering creates a predictable prompt-injection attack surface whose vulnerability increases monotonically with steering magnitude, a concern for agent systems deploying steered classifiers.

arXiv cs.AI / cs.LG / cs.CL · 20h agoAI research

QoS-Aware Federated Learning for Multimodal In-Cabin Interaction in Smart Vehicles

Researchers propose FedQoS, an asynchronous event-triggered federated learning framework for smart vehicles that cuts communication overhead 76.7% and latency 26.0%.

Researchers propose FedQoS, an asynchronous, event-triggered federated learning framework for multimodal in-cabin vehicle systems. It uses a resource-aware training gate and a QoS-aware transmission policy so learning never compromises vehicle mobility or energy reserves, with a staleness-aware proximal term handling update age. On multimodal vehicular datasets it matches FedAvg accuracy while cutting communication overhead by 76.7% and latency cost by 26.0%.

arXiv cs.AI / cs.LG / cs.CL · 1d agoAI research

Perception, Layout, and Validation: Calibrated Confidence for Reliable Straight-Through Processing of Financial Documents

A decomposed perception-layout-validation confidence score with conformal risk control lets VLMs auto-approve 49-72% of financial document fields at target error.

The paper proposes a decomposed confidence layer over VLM-extracted financial document fields using perception, layout, and validation channels plus conformal risk control for reliable straight-through processing. Tested on invoices and ad-buy forms with Qwen3.6-27B and Gemini-3.1-Flash-Lite, AUROC improves from 0.54-0.74 to 0.90-0.99. The method auto-approves 49-72% of fields at sub-10% empirical error versus only 0.1-7.0% for native VLM verbalized confidence.

arXiv cs.AI / cs.LG / cs.CL · 1d agoAI research

Google Research Introduces Retrieve-for-Train (R4T): An RL-Compiled Diffusion Retriever for 12× to 20× Faster Query Fan-Out

Google Research introduced R4T, an RL-trained fan-out pipeline distilled into a 53.9M-parameter diffusion retriever achieving 12x-20x faster query fan-out.

Google Research introduced Retrieve-for-Train (R4T), which trains a fan-out language model with GRPO plus soft PPO regularization, then distills query fan-out into a 53.9M-parameter diffusion transformer that generates all retrieval embeddings in a single non-autoregressive pass. A three-term reward (groundedness 0.6, diversity 0.2 via Vendi Score, alignment 0.2) prevents paraphrastic collapse and reward hacking during training. On the Polyvore dataset, Gemma3-4B R4T-FOLM averaged 49.1 versus 40.9 for Best-of-N, and the diffusion retriever cut fan-out latency from 1.46s to 0.07s at batch size 8, a consistent 12x-20x speedup over autoregressive methods.

MarkTechPost · 1d agoAI research1

Stanford Researchers Release Paper2Agent: Turning Research Papers Into AI Agents That Reproduce Results and Run on New Data

Stanford researchers released Paper2Agent, a Nature-published pipeline that turns research papers into MCP servers agents can execute.

A Stanford team led by Jiacheng Miao and James Zou published Paper2Agent in Nature on 16 September 2026. Built on Claude Code's agent SDK, it converts a paper and its codebase into a Model Context Protocol server with validated tools, resources, and prompts. In benchmarks, the AlphaGenome agent built 22 tools in about 45 minutes for US$14, scored 100% on 15 novel queries versus 78.7% for Claude Code with repository access, and cut median runtime 1.9x. In scale tests, 74 of 100 bioRxiv papers were converted and 593 of 599 proposed tools passed validation.

MarkTechPost · 1d agoAI research1

Don't Mask the Environment: Observation Supervision Changes How Agents Explore Under RL

ActObs adds observation-token supervision to SFT, yielding higher pass@k for Qwen3 agents after GRPO on Terminal-Bench 2.0 and code editing.

Researchers introduce ActObs, an SFT variant that supervises environment-observation tokens in agent trajectories in addition to action tokens, without extra data, parameters, tokens, or forward passes. On Qwen3-4B, GRPO initialized from ActObs achieves higher pass@k at every sampling budget on Terminal-Bench 2.0, and on Qwen3-8B it trades some pass@1 for +3.4 pp at pass@16 while solving more distinct tasks. The benefit transfers to unseen code-editing tasks on aider-polyglot (+4.2 pp pass@1 at 4B scale). The authors trace the advantage to gradient analysis showing joint supervision preserves environment prediction and policy entropy, improving downstream RL exploration.

Hugging Face daily papersupdated · 20h agofirst · 1d agoAI research 2 sources

Evidence-Grounded Agentic Formulation Development in an Autonomous Laboratory

Andromeda 2, an agentic laboratory system, reaches a 50% high-performance hit rate for paclitaxel SEDDS formulations versus 17% for its predecessor and 2% for DoE.

Andromeda 2 is an agentic system that reasons over structured in-house experimental evidence and invokes computational and experimental tools to design and execute successive formulation batches for self-emulsifying drug delivery systems (SEDDS). For paclitaxel it achieved a 50% high-performance hit rate versus 17% for Andromeda 1 and 2% for a wet-lab DoE campaign, identifying 12 formulations meeting all four target product profile objectives versus 6 and 0. A selected full-TPP formulation reached approximately 19% w/w apparent paclitaxel loading, about 3.3-fold higher than a published paclitaxel S-SEDDS, and an ablation showed structured evidence access increased mean AUC by 34%.

arXiv cs.AI / cs.LG / cs.CL · 1d agoAI research

Long-Lived Characters, Local Inference: Incremental Memory Maintenance for Game NPCs

Researchers present incremental KV-cache memory maintenance for long-lived game NPCs running locally on a quantized Qwen hybrid model.

The paper studies incremental memory maintenance for long-lived game NPCs deployed locally with a quantized Qwen hybrid recurrent-attention language model. The runtime removes superseded attention KV entries, computes replacement records at the true sequence tail, and preserves the continuing recurrent state and unchanged KV. Experiments across eight scripted maintenance rounds show true-tail updates preserve current-state and historical bindings, while slot-preserving alternatives repeat a double-subtraction error.

arXiv cs.AI / cs.LG / cs.CL · 1d agoAI research

What Breaks Under Pruning in Smart Homes, and When? Evaluating LLM Degradation Across Architectures and Task Complexity

Pruning study across four LLM architectures finds dense models degrade sharply on smart-home tool calling while MoE models tolerate far more.

Researchers systematically study pruning-induced degradation in smart-home tool calling across four LLMs spanning dense Transformer, dense hybrid, and mixture-of-experts architectures, combining depth, width, hybrid, and expert pruning methods, and evaluate over 19,500 instances from three datasets after post-pruning supervised fine-tuning. Dense models show narrow safe pruning regions followed by sharp degradation, while MoE models tolerate substantially more pruning. Pruning degrades grounded specificity (operation, device, argument, value) before schema-level intent, and aggressive dense pruning can induce systematic over-refusal.

arXiv cs.AI / cs.LG / cs.CL · 2d agoAI research

FlashVector: Agent for Hierarchical Model Serving Stack Optimization

FlashVector agent optimizes all layers of Unity's ad-serving stack, delivering up to 2x model-server throughput and 1.98x latency speedup in production.

FlashVector is an agentic system that optimizes performance across GPU kernels, ML framework computation graphs, model servers, and on-demand feature processing. Deployed in Unity's Vector advertising platform, it achieved up to 2x model-server throughput increase, 1.98x latency speedup, and 1.6x feature-store throughput gain. Optimizations spanned NVIDIA Triton's C++ codebase and the Python feature transformation service, demonstrating extensibility beyond single-kernel tuning.

arXiv cs.AI / cs.LG / cs.CL · 2d agoAI research1