Marr
PulseAugur coverage of Marr — every cluster mentioning Marr across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
AI research reveals counterintuitive findings on observation fidelity, consciousness, and reasoning reliability
New research indicates that increasing the fidelity of observations can paradoxically harm the problem-solving abilities of embodied Large Language Models (LLMs), with one study finding raw RGB input to be more effectiv…
-
Paper argues Surprisal Theory is not representation-agnostic for LLMs
A new paper argues that Surprisal Theory, often framed as a computational-level explanation, is not truly representation-agnostic, especially in the context of large language models (LLMs). The authors contend that the …
-
New MARR technique boosts low-bit quantization for LLMs and ViTs
Researchers have developed a new technique called Module-Adaptive Residual Reconstruction (MARR) to improve low-bit post-training quantization for large language models and vision transformers. MARR addresses limitation…