arXiv:2607.26661v3 Announce Type: replace Abstract: Ascend C operator optimization is critical for NPU (Neural Processing Unit) inference performance but…
Author: script
DiffImaginE: Imagine to Verify Entity Types with Diffusion
arXiv:2608.03025v3 Announce Type: replace Abstract: Multimodal named entity recognition (MNER) determines whether each candidate span and entity-type…
Do LLMs Know Their Vulnerable Scenarios?
arXiv:2607.23496v2 Announce Type: replace Abstract: Safety-aligned large language models are trained to refuse harmful requests, yet embedding the same…
Nvidia’s new $500B plan is risky but brilliant, especially for aging GPUs
Nvidia has a plan to make sure its GPUs won’t lose value. It wants to convince a new crop of financiers to keep lending for AI buildouts.
DAPD: Dual-Anchored Policy Distillation
arXiv:2608.01735v2 Announce Type: replace Abstract: On-policy (self) distillation (OPSD) is increasingly adopted for language-model post-training. It…
AI News Brief Hourly Summary 2026-08-15 04h : 13 posts
13 posts published in the last hour 01:32Alipay-PIBench: A Realistic Payment Integration Benchmark for Coding Agents 01:32Similarity All The Way Up: Multilingual Generalization in LLMs Relies on Language-Level Similarity Structures 01:32Residual Modeling for High-Fidelity Learned Compression of Scientific Data 01:31Learning…
Alipay-PIBench: A Realistic Payment Integration Benchmark for Coding Agents
arXiv:2607.14573v4 Announce Type: replace Abstract: Payment integration is a demanding repository-level software task: agents must select a suitable…
Similarity All The Way Up: Multilingual Generalization in LLMs Relies on Language-Level Similarity Structures
arXiv:2607.22699v2 Announce Type: replace Abstract: As Large Language Models (LLMs) grow more capable across diverse tasks, their (in)ability to…
Residual Modeling for High-Fidelity Learned Compression of Scientific Data
arXiv:2606.05389v2 Announce Type: replace Abstract: Lossy compression is essential for massive spatiotemporal data from scientific simulations. Learned…
Learning to Recover Task Experts from a Multi-Task Merged Model
arXiv:2606.26902v2 Announce Type: replace Abstract: Multi-task model merging aims to consolidate several task-specific experts into a unified model, yet…