This paper proposes a source-free continual test-time adaptation methodology using a controlled teacher adaptation and class prototype estimation.

The paper introduces FoLoRA, a novel optimization framework that uses a generalized Rayleigh quotient to achieve a superior balance between adapting foundation models to specific tasks and preserving…

This paper introduces Accessibility Plasticity, a principle of adaptive computation that allows systems to adapt by reorganizing which existing computations can interact and participate, reducing the…

HarnessForge introduces a meta-adaptive framework that jointly evolves the execution structure (harness) and the reasoning policy of LLM agents, significantly improving overall system performance acro…

GLOVES is a flow-based adaptation method that selectively corrects non-expert robot actions by guiding them toward a task-specific expert action distribution, thereby improving performance while maint…

This paper introduces Test-Time Harness Evolution (TTHE), a method for optimizing LLM agent harnesses during evaluation using execution traces, without requiring gold labels or training.

CORTIS is a text-only adaptation framework that fine-tunes spoken language models for task-oriented voice agents using text-form task supervision.

The study demonstrates that domain adaptation primarily reshapes the linguistic explanatory framework of language models, causing shifts in cosmological stance secondarily, rather than directly modify…

The paper introduces Entropic Projection Alignment (EPA), a unified framework that estimates, explains, and improves model performance under distribution shift by aligning source and target distributi…

TIMEGATE introduces a resource-aware policy layer that manages continual ML adaptation by dynamically budgeting time and evaluation resources, achieving significant compute and energy savings without…

The paper distinguishes between a model's ability to generate useful updates for external agent components (harness-updating) and its ability to benefit from those updates (harness-benefit), finding t…

Adaptive data selection significantly improves wearable prediction performance, particularly for individuals with poor baseline health metrics, suggesting that selective data sampling should be tailor…

This paper analyzes the regret of a NeuroEvolutionary Online Learning (NEOL) framework for learning neural network architectures and weights, achieving sublinear regret under mild conditions.

This paper introduces Anchored Weight Decay (AWD), a regularization technique that effectively prevents prior-task forgetting during LLM fine-tuning with Evolution Strategies (ES), positioning ES as a…

The paper demonstrates that Low-Rank Adaptation (LoRA) is an effective and superior method for adapting large, pretrained Transformer surrogates for automotive aerodynamics to new vehicle families usi…

Adaptive Auto-Harness introduces a framework that enables LLM agents to sustain self-improvement and maintain high performance over open-ended, shifting task streams, outperforming existing fixed-benc…

The paper proposes HiSME, a lightweight hierarchical skill meta-evolving solution that jointly optimizes skills and the skill evolving strategy by learning meta-skills from task execution traces, lead…

JenBridge is a novel, adaptive framework that generates high-fidelity, long-form video soundtracks, significantly improving narrative coherence and naturalness across scene transitions.