last
PulseAugur coverage of last — every cluster mentioning last across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
LAST transformer model enhances audio recognition with iterative refinement
Researchers have developed the Looped Audio Spectrogram Transformer (LAST), a novel transformer model designed to improve audio recognition efficiency. LAST processes all audio tokens initially and then iteratively refi…
-
New LaST framework enhances zero-shot surgical phase recognition
Researchers have developed a novel framework called LaST (Large-Small Temporal adaptation) to improve zero-shot surgical phase recognition. This approach combines the strengths of large foundation models, which offer br…
-
New methods prune visual tokens for efficient MLLM inference · 4 sources tracked
Researchers have developed several new methods to efficiently prune visual tokens for multimodal large language models (MLLMs), aiming to reduce inference costs and latency. The LAST framework uses the last query token'…
-
Final launches $8,999 diamond-diaphragm headphones
Final has launched its new flagship DX10000 CL headphones, featuring a 40mm True Diamond diaphragm driver for enhanced audio fidelity and reduced distortion. The limited Collector's Edition, priced at $8,999, includes p…
-
AI Shopping Agents Face Hurdles Amid Security and Standardization Challenges
The widespread adoption of AI shopping agents is being hindered by significant security concerns, a lack of standardized protocols for agentic commerce, and retailer policies. Experts at a Fortune Brainstorm Tech panel …
-
Researchers develop new methods for person re-identification despite clothing changes
Two new research papers tackle the challenge of clothes-changing person re-identification (CC-ReID), a problem where individuals need to be recognized despite variations in their attire. The first paper, Ortho-ReID, int…