MMAU-Pro
PulseAugur coverage of MMAU-Pro — every cluster mentioning MMAU-Pro across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
New research advances audio representation learning and classification · 4 sources tracked
Three new research papers explore advancements in audio representation learning and classification. One paper introduces TAPE, a system for estimating audio effect parameters from processed audio, achieving faster proce…
-
SkillFormer adapts audio language models with skill-specific adapters
Researchers have developed SkillFormer, a novel approach to adapt audio language models for diverse tasks. This method decomposes audio understanding into skill-specific adapters that are composed at inference time via …
-
AdaLoop enhances audio language models with adaptive reasoning
Researchers have developed AdaLoop, a novel module designed to enhance the reasoning capabilities of large audio language models. This module adaptively determines the necessary depth of computation for audio-related qu…
-
Realtime-Venus system enables full-duplex interaction with dual AI models · 2 sources tracked
Researchers have introduced Realtime-Venus, a novel full-duplex interaction system designed for more natural human-computer communication. The system utilizes two specialized 9B models: Realtime-Venus-Omni for audio-vis…
-
New LALM model achieves competitive multimodal performance with instruction-free alignment
Researchers have developed a novel approach to creating multimodal large language models (MLLMs) by focusing solely on alignment, bypassing traditional multi-stage pipelines. This new method, termed LALM, trains only a …
-
ParaBridge method improves speech models' paralinguistic understanding
Researchers have developed ParaBridge, a novel on-policy self-distillation method designed to improve speech language models' ability to incorporate paralinguistic cues into dialogue. This technique trains models to bet…
-
HeadRouter prunes audio tokens in LLMs by routing attention heads
Researchers have introduced HeadRouter, a novel method for compressing large audio language models by dynamically pruning audio tokens. Unlike previous approaches that assume uniform head importance, HeadRouter recogniz…