Split
PulseAugur coverage of Split — every cluster mentioning Split across labs, papers, and developer communities, ranked by signal.
2 day(s) with sentiment data
-
AutoProfiler learns GPU kernel optimization by selecting relevant hardware metrics
Researchers have developed AutoProfiler, a framework designed to optimize GPU kernel performance by intelligently selecting which hardware information to profile. Unlike previous methods that relied on fixed or extensiv…
-
New SPLIT method optimizes AI model testing compute allocation
Researchers have developed a new method called SPLIT to optimize the allocation of computational resources during the testing phase of language models and agents. SPLIT addresses the challenge of imperfect verifiers, wh…
-
New SPL language unifies LLM orchestration and symbolic computation
Researchers have introduced SPL (Structured Prompt Language), a novel declarative language designed to unify deterministic and probabilistic computation within a single specification. Unlike existing frameworks that sep…
-
New SPLIT method detects AI-generated and edited videos with high accuracy
Researchers have developed SPLIT, a new training-free method for detecting AI-generated and partially edited videos. SPLIT utilizes a frozen vision encoder to analyze spatial patch-level incoherence and temporal roughne…
-
New benchmark SPLIT tests LLM empathy in English and Ukrainian
A new benchmark called SPLIT has been developed to evaluate the cross-lingual empathy and cultural grounding of Large Language Models (LLMs) in crisis-related situations, specifically focusing on English and Ukrainian. …
-
Robotics research introduces low-cost tactile sensors and advanced simulation tools
Researchers have developed FlexiTac, an open-source, low-cost tactile sensing system for robots. This system uses flexible sensor pads and a compact readout board to provide dense, real-time tactile data, enabling advan…