Zeng et al.
PulseAugur coverage of Zeng et al. — every cluster mentioning Zeng et al. across labs, papers, and developer communities, ranked by signal.
-
GLM-4-Voice uses RL to achieve state-of-the-art spoken math reasoning
Researchers have applied reinforcement learning to the GLM-4-Voice speech model to improve its mathematical reasoning capabilities. After supervised fine-tuning on spoken question-answering data, the model showed improv…
-
LVLMs struggle with implicit communication, new studies show
Two recent studies on Large Vision-Language Models (LVLMs) in referential communication have yielded conflicting results regarding their ability to coordinate efficient referring expressions. One paper, by Jones et al.,…
-
New method reduces positional bias in dense retrieval models
Researchers have developed a method to mitigate positional bias in dense retrieval models, a common issue where retrieval effectiveness decreases as relevant information appears later in a passage. This new technique, a…