Qwen 2.5:1.5B
PulseAugur coverage of Qwen 2.5:1.5B — every cluster mentioning Qwen 2.5:1.5B across labs, papers, and developer communities, ranked by signal.
2 day(s) with sentiment data
-
New RL method boosts LLM event forecasting performance
A new research paper introduces Group Relative Policy Optimization (GRPO), a reinforcement learning method designed to enhance the forecasting capabilities of Large Language Models (LLMs). Experiments show that a 1.5B p…
-
LLM inference efficiency explored on edge devices and cloud GPUs
Two new research papers explore the challenges of running large language models (LLMs) efficiently. The first paper investigates the performance trade-offs of deploying LLMs on edge devices like smartphones and speciali…
-
New Audit Method Reveals Inconsistent AI Model Refusals to Hazardous Content
A new research paper introduces BioRefusalAudit, a method to evaluate the robustness of AI model refusals to hazardous content. The study found that many models' refusals are inconsistent, collapsing under minor prompt …
-
DDR5 Bandwidth Bottlenecks Dual-LLM Inference on AMD APUs
A developer's experiment revealed that the DDR5 bandwidth on AMD APUs significantly limits the performance of running multiple large language models simultaneously. Despite a 35-billion-parameter model like Qwen 3.6:35B…
-
Researchers Unveil LoRA Adapter Backdoor Attacks and Detection Methods
A new research paper details how LoRA adapters, commonly used for fine-tuning large language models (LLMs), can be compromised through training data poisoning. This attack can introduce backdoors that preserve the model…
-
New Hybrid AI Architecture Enhances Wind Turbine Blade Inspection
Researchers have developed a novel hybrid architecture for automated industrial inspection, specifically for wind turbine blade maintenance. This system integrates a vision model for defect localization with a language …
-
Hybrid AI pipeline automates wind turbine blade defect reporting
Researchers have developed a novel pipeline for automated industrial inspection, specifically for wind turbine blades. This system integrates a vision model for defect localization with a language model for generating s…
-
LoRA rank allocation fails in RL fine-tuning, study finds
A new study on the Qwen 2.5 1.5B model reveals that adaptive rank allocation techniques, effective in supervised fine-tuning, do not translate to reinforcement learning with Group Relative Policy Optimization (GRPO). Re…