Qwen2.5-72B-Instruct
PulseAugur coverage of Qwen2.5-72B-Instruct — every cluster mentioning Qwen2.5-72B-Instruct across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
New Hierarchical Multi-Agent System Enhances Depression Detection
Researchers have developed HiMA-MDD, a novel hierarchical multi-agent system designed for interpretable multimodal depression detection in clinical interviews. This system organizes evidence gathering and assessment int…
-
AI models improve human value detection using Schwartz theory geometry
Researchers have developed a new method called Schwartz-Geometry Decoding to improve human value detection in AI models. This approach leverages the theoretical structure of Schwartz values, which describes them as a co…
-
FormalRewardBench benchmark evaluates LLM reward models for theorem proving
Researchers have introduced FormalRewardBench, a new benchmark designed to evaluate reward models used in formal theorem proving. This benchmark addresses the challenge of sparse credit assignment in reinforcement learn…