Latest AI/ML News
9894 articles · arXiv cs.LG
arXiv:2610.00742v1 Announce Type: cross Abstract: Every protein has a unique stability landscape, but the physical consequences of mutation are govern…
arXiv:2610.00738v1 Announce Type: cross Abstract: The Straight-Through Estimator (STE) is a widely used heuristic for Quantization-Aware Training (QAT…
arXiv:2610.00727v1 Announce Type: cross Abstract: Controlling an agent with vision requires being able to separate useful information from irrelevant…
arXiv:2610.00724v1 Announce Type: cross Abstract: Language models learn content and style jointly, making stylistic variation in their outputs difficu…
arXiv:2610.00706v1 Announce Type: cross Abstract: Large audio-language models (LALMs) are sensitive to input perturbations, such as noise, waveform co…
arXiv:2610.00700v1 Announce Type: cross Abstract: Recent advances in AI for scientific discovery enable molecular understandingand design, yet reasoni…
arXiv:2610.00695v1 Announce Type: cross Abstract: Secure aggregation lets a server recover an aggregate of client updates without observing any indivi…
arXiv:2610.00694v1 Announce Type: cross Abstract: Compression reports summarize how far a compressed language model moved from the dense one, usually…
arXiv:2610.00693v1 Announce Type: cross Abstract: Federated learning (FL) has recently attracted increasing attention in remote sensing (RS) since it…
arXiv:2610.00687v1 Announce Type: cross Abstract: Hardware-operable failures (HOFs) interrupt large language model (LLM) training but permit recovery…
arXiv:2610.00686v1 Announce Type: cross Abstract: Recent video-based world models pair the scalability of autoregressive (AR) prediction with the visu…
arXiv:2610.00685v1 Announce Type: cross Abstract: With the rapid adoption of large language models (LLMs) and parameter-efficient fine-tuning (PEFT) m…
arXiv:2610.00682v1 Announce Type: cross Abstract: Large language models (LLMs) increasingly underpin scientific AI applications that reason over struc…
arXiv:2610.00678v1 Announce Type: cross Abstract: Histological whole-slide images (WSIs) are central to computational pathology but pose severe comput…
arXiv:2610.00663v1 Announce Type: cross Abstract: Backdoored large language models (LLMs) can behave normally on benign inputs while producing attacke…
arXiv:2610.00654v1 Announce Type: cross Abstract: Personalization has long relied on customer data to infer what an individual is likely to value. We…
arXiv:2610.00651v1 Announce Type: cross Abstract: Agent evaluations are increasingly used to compare LLMs and inform deployment decisions, yet ranks c…
arXiv:2610.00649v1 Announce Type: cross Abstract: Synthetic speech detection is critical for audio security, but performance can degrade when labeled…
arXiv:2610.00636v1 Announce Type: cross Abstract: Evaluating AI agents on scientific research tasks is constrained by the time and resources required…
arXiv:2610.00610v1 Announce Type: cross Abstract: Explainable suicide-risk assessment requires models not only to estimate risk severity, but also to…