arXiv:2604.09408v3 Announce Type: replace
Abstract: Frontier coding agents solve complex tasks when given complete context but collapse when specifications are incomplete or ambiguous. The bottleneck is not raw capability, but judgment: knowing when t…
arXiv:2604.19606v2 Announce Type: replace
Abstract: Systematic ablations are essential to attribute performance gains in AI Virtual Cells, yet they are rarely performed because biological repositories are under-standardized and tightly coupled to doma…
arXiv:2505.17056v2 Announce Type: replace-cross
Abstract: As large language models (LLMs) are increasingly integrated into educational tools, current evaluations on standardized tests predominantly focus on binary outcome accuracy. Instead, an effecti…
arXiv:2604.27117v1 Announce Type: cross
Abstract: Recommender systems increasingly incorporate textual reviews to enrich user and item representations. However, most review-aware models remain optimized for rating prediction rather than ranking qualit…
arXiv:2508.21787v2 Announce Type: replace-cross
Abstract: Best-of-n sampling improves the accuracy of large language models (LLMs) and large reasoning models (LRMs) by generating multiple candidate solutions and selecting the one with the highest rewa…
arXiv:2510.12476v3 Announce Type: replace-cross
Abstract: Large language models (LLMs) have grown more powerful in language generation, producing fluent text and even imitating personal style. Yet, this ability also heightens the risk of identity impe…
arXiv:2510.20933v2 Announce Type: replace-cross
Abstract: Medical image segmentation is essential for clinical applications such as disease diagnosis, treatment planning, and disease development monitoring because it provides precise morphological and…
arXiv:2604.27115v1 Announce Type: new
Abstract: Neuron pruning is widely used to reduce the computational cost and parameter footprint of large language models, yet it remains unclear whether neurons in task-specific models contribute uniformly to tas…
arXiv:2604.27043v1 Announce Type: new
Abstract: Today’s AI assistants such as OpenClaw are designed to handle context effectively, making context learning an increasingly important capability for models. As these systems move beyond professional setti…
arXiv:2604.27232v1 Announce Type: new
Abstract: Models of sign language have historically lagged behind those for spoken language (text and speech). Recent work has greatly improved their performance on tasks like sign language translation and isolate…