Tag
Omni-IO Skills presents a plug-and-play agent harness that enables omni-native capabilities across multiple modalities, significantly improving performance on multimodal benchmarks like UniM-90 without changing the agent's core reasoning.
The tweet describes the goal of ODS to make local AI deployment seamless and plug-and-play across various hardware, models, and kernel optimizations, while celebrating almost 6,000 GitHub stars.
RunAnywhere enables users to run AI models on a Mac and stream inference to an iPhone over the local network with one-click setup, avoiding cloud dependency for low latency.
This paper introduces PAYN, a plug-and-play token compression method for MLLM-based referring expression segmentation that relies solely on position information, outperforming existing techniques by preserving spatial relational consistency.
EnvHarness is a programmable wrapper framework that dynamically adapts static environments to enhance LLM agent training, outperforming existing methods by providing superior optimization signals for reinforcement learning across multiple benchmarks.
This paper introduces a plug-and-play 2D motion interface that enables pretrained motion language models to process 2D inputs from monocular videos without retraining, improving real-world applicability.
Security researchers release a DEF CON 34 talk and tooling showing that Windows Plug and Play can silently download and execute vendor code as SYSTEM via attacker-controlled device identities, including through USB emulation and RDP USB redirection.
PILA reformulates LLM-native advertising as a conditional response rewriting problem, decoupling ad insertion from upstream generation via a lightweight, model-agnostic sidecar module that preserves response quality while enabling controllable ad exposure.
Introduces a training-free method for enhancing safety alignment of LLMs by using knowledge distillation and model fusion to prevent shadow alignment, improving defense success rate by 14.42% on harmful question datasets without compromising performance.
Arduino has launched new plug-and-play modules designed for long-range sensor projects, simplifying IoT development.
PnP-CoSMo is a plug-and-play framework for multi-contrast MRI reconstruction that learns content/style models from image data, enabling reconstruction without raw k-space training data. It is generalizable across contrasts and forward operators.
This paper introduces a proactive memory agent that runs alongside an action agent to prevent behavioral state decay in long-horizon tasks, achieving significant improvements on Terminal-Bench2.0 and τ^2-Bench. The authors also train Qwen3.5-27B using SFT and GRPO as an early step toward open-weight memory policies.
MIThinker proposes a lightweight reasoning model for motivational interviewing counseling agents, trained via supervised fine-tuning and reinforcement learning to generate therapeutic thoughts, achieving MI competency comparable to state-of-the-art systems with lower computation.
ResilPhase is a training-free acceleration framework for diffusion models that reformulates accelerated inference as stable macro-trajectory extrapolation in ODE space, using derivative-free barycentric Lagrange extrapolation and bounded phase mapping to achieve state-of-the-art fidelity under high acceleration ratios.
This paper introduces SP³, a method using Spherical Encoder priors for Plug-and-Play image restoration, achieving perceptual quality comparable to zero-shot diffusion priors while being 3–630× faster across tasks.
Introduces Face-Fairness (FF), a plug-and-play framework for bias mitigation in deepfake detection, featuring Face-Feature Tuning (FFT) as the first demographic label-free fairness method that improves group accuracy and reduces performance gaps across demographics.
NGM is a training-free, plug-and-play memory module for LLMs that enhances performance by using pretrained token embeddings for N-gram knowledge retrieval without additional training or retrieval pipelines, achieving gains of up to 3 points on code generation and knowledge tasks.
This paper introduces Sequential Agent Tuning (SAT), a coordinator-free training paradigm for multi-LLM teams that provides monotonic improvement guarantees and plug-and-play invariance, enabling smaller models to outperform larger ones.
This paper introduces ReBalance, a training-free, plug-and-play method that dynamically balances overthinking and underthinking in large reasoning models, improving efficiency and accuracy across multiple benchmarks.