Topic: optimization
7 stories found
Yesterday
KDASO: Knowledge-Data Dual-Driven Automated Skill Optimization for Liability Adjudication Tasks
KDASO is a new method that uses both knowledge and data to automatically optimize skills for determining liability in tasks like legal charge determination, leveraging the potential of Large Language Models to enhance accuracy and efficiency in these complex analyses. This matters because it could significantly improve the precision and speed of liability adjudication processes in legal settings.
Thursday, November 5, 2026
Flipsnack grows product signups with conversion optimization
Flipsnack increased product signups by optimizing its ChatGPT Ads campaigns, successfully growing registrations while reducing the cost per signup. This strategy highlights the effectiveness of targeted advertising in enhancing user engagement and improving conversion rates.
Monday, November 2, 2026
Li$^{2}$SAO: Lifting Light Singl-Rollout Asynchronous RL Optimization via Group-Relative Actor-Critic Bootstrapping
A new method called Li$^{2}$SAO aims to enhance asynchronous reinforcement learning optimization for large language models by using a Group-Relative Actor-Critic bootstrapping approach, potentially improving training efficiency. This development is significant as it addresses limitations in current techniques and could lead to more effective post-training processes for LLMs.
Saturday, October 31, 2026
Understanding Large Language Models as Numerical Optimizers
A new study suggests large language models (LLMs) could be used as numerical optimizers, potentially revolutionizing how complex problems are solved. However, the full extent of their capabilities and limitations, especially in high-dimensional spaces, remains unclear.
Thursday, October 29, 2026
ggml/llama.cpp releases: b11986
The ggml/llama.cpp project added initial OpenCL support for IQ2, enhancing matrix multiplication methods specifically for Adreno GPUs. This update is crucial as it broadens the library's compatibility and performance on mobile devices with Adreno hardware.
Monday, October 26, 2026
ggml/llama.cpp releases: b11909
ggml/llama.cpp released a new version with optimizations for row skipping in matrix multiplication, improving performance. These updates are significant for enhancing computational efficiency in large language model training.
Wednesday, August 26, 2026
vLLM releases: v0.28.0
vLLM released version 0.28.0 with significant optimizations, including Decode Context Parallel (DCP) support and fused FlashKDA decode and prefill kernels, benefiting from 584 commits by 270 contributors. This update enhances performance, particularly for Kimi-K3, highlighting the community's contribution to the project.
🌿 That's all for now. Come back tomorrow.
7 of 7 items shown. Sources: 169 days indexed.