Queries
PulseAugur coverage of Queries — every cluster mentioning Queries across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
New RACE method compresses LLM attention for faster, more efficient inference
Researchers have developed RACE, a novel method for compressing attention mechanisms in large language models by reducing the dimensionality of query and key vectors. This technique, based on joint query-key activation …
-
New RotateAttention framework speeds up AI video generation
Researchers have developed RotateAttention, a novel mixed-precision INT4 FlashAttention framework designed to accelerate DiT-based video generation models that utilize 3D Rotary Position Embeddings (3D RoPE). The framew…
-
New PORTS method enhances LLM tool selection accuracy
Researchers have developed PORTS, a new method for training retrievers to better select tools for large language models (LLMs). Existing retrievers are often misaligned with LLMs due to separate training processes. PORT…
-
Keyless Attention mechanism halves KV cache and boosts transformer efficiency
Researchers have introduced Keyless Attention, a novel attention mechanism for transformers that eliminates the key projection entirely, operating solely on queries and values. This approach results in a Value-Only Cach…