cập nhật 42 phút trước

⏱ Độ trễ thật của tab này: trung bình 6.6 giờ sau khi CVE được công bố (n = 5196, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.

24
A CPU Inside an LLM: Zero-Gradient Compilation of Exact Circuits into Pretrained Weights
📄 Paper HF Daily Papers 2 ngày trước

Pretrained language models (LMs) remain unreliable on exact multi-digit arithmetic without gradient fine-tuning or external tool interpreters. We introduce closed-form, zero-gradient circuit-grafting primitives that compile deterministic computation directly into pretrained LM we…

🅲 hạng C
22
Training Vision Models for LLM-Driven Weight-Space Programming
📄 Paper HF Daily Papers 2 ngày trước

It has been demonstrated that, in certain settings, large language models can perform weight-space programming to directly modify the weights of neural networks. However, it is unknown how dedicated training of these networks can contribute to the successes of weight-space progra…

🅲 hạng C
21
General progress substitutes for specific training data in language models
📄 Paper HF Daily Papers 3 ngày trước

Language models acquire their capabilities from training data, and developers withhold data during training to keep models from learning capabilities that could be misused. How long this delays a capability, and how much data is needed to acquire it later, is unknown. Here we sho…

🅲 hạng C
20
Let Samples Sing in Chorus: Mitigating Spurious Correlations via Cross-view Consensus
📄 Paper HF Daily Papers 4 ngày trước

Deep models often rely on spurious correlations that fail on underrepresented groups. Existing methods either correct human-specified bias attributes or infer unknown biases from the learned representation space. However, annotated attributes may differ from the shortcuts actuall…

🅲 hạng C