…AI-generated summary Parameter-efficient adaptation of pretrained vision models is commonly performed through linear probes, prompts, low-rank updates, or lightweight residual modules. While effective, these methods usually treat adaptation as…
…Generated by Qwen/Qwen2.5-Coder-32B-Instruct LLM agents increasingly retrieve externally curated skills-procedural instructions retrieved at decision time-to improve performance on long-horizon interactive tasks. Existing skill libraries…
…View arXiv page View PDF Project page GitHub 98 Add to collection Community Less number of 3D Gaussians, better performance Get this paper in your agent: hf papers read 2606.05102 Don…
…Across 11 image editing models, we find overall low performance, with the current highest-performing industry leader scoring only 17.1% (mIoU). Task decomposition reveals especially challenging operation types (geometric transformation, most…
…Our approach consistently improves LLM performance across multiple tasks, including instruction following and math reasoning, in both training free and fine tuning settings. Moreover, we show that our method mitigates attention sinks…
…Lei Yang , , Abstract Multi-domain reinforcement learning in language models causes performance degradation through shared computational pathways, but targeted refresh and rollback techniques can selectively recover lost capabilities with minimal side effects…
…Across these settings, κ- SwiGLU improves mean CORE performance while adding negligible parameters and incurring only a small computational overhead, demonstrating that confidence-aware gate sharpness is a promising mechanism for improving…
…Similar to dataset contamination, where benchmark exposure leads to higher performance through memorization , we hypothesize that models trained on texts describing evaluation practices may implicitly learn to recognize and respond to evaluation…
…Yu-Hsi Chen , Abstract CPCANet is a domain generalization framework that uses Common Principal Component Analysis to discover structured domain-invariant subspaces through differentiable neural layers, achieving state-of-the-art performance…
…Existing acceleration methods either require costly retraining with architectural changes or suffer from severe performance drop at high sparsity due to train-inference mismatch. To address these limitations, we propose BEAM (Binary…