Hao Wang
PulseAugur coverage of Hao Wang — every cluster mentioning Hao Wang across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
New AI research explores reactive optimizers, video memory benchmarks, and efficient network architectures
Researchers have developed OPAL, a reactive optimizer that uses a language model agent to dynamically adjust training rules and schedules for individual parameter groups during a single training run, showing promise in …
-
New Quadratic Direct Forecast algorithm improves time-series modeling
Researchers have introduced a novel Quadratic Direct Forecast (QDF) learning algorithm designed to improve multi-step time-series forecasting models. This method addresses limitations in existing objectives like mean sq…
-
New loss functions improve time-series forecasting accuracy · 2 sources tracked
Two new research papers propose novel loss functions for time-series forecasting models to improve accuracy and efficiency. The first paper introduces Time-o1, which transforms label sequences into decorrelated componen…
-
New FreDF method forecasts time series by learning in frequency domain
Researchers have introduced FreDF, a novel approach to time series forecasting that addresses the overlooked issue of autocorrelation among future labels. Unlike traditional Direct Forecast (DF) methods that predict fut…
-
AI models hampered by outdated data, real-time search is the solution
Large language models (LLMs) are hindered by knowledge cutoffs, meaning their training data is outdated by the time they are released. This limitation, even for advanced models like Anthropic's Claude 4.7 Opus trained o…
-
$M^2PO$ framework enhances LLM machine translation accuracy
A new framework called $M^2PO$ has been developed to improve machine translation by Large Language Models (LLMs). This method addresses a key issue where current models often favor fluent but inaccurate translations, ov…
-
New 'Effective Number of Nonzeros' metric introduced for sparse recovery
This paper introduces the Effective Number of Nonzeros (ENZ), a new metric for measuring sparsity in data. ENZ is derived from the Shannon entropy of coefficient magnitudes and provides a more nuanced understanding of s…
-
New Med-R2 strategy enhances AI medical report generation accuracy
Researchers have introduced Med-R2, a novel fine-tuning strategy designed to improve automated medical report generation (MRG) using large vision-language models (LVLMs). This approach addresses limitations in current m…
-
COMPASS framework tackles missing data in multimodal sensing
Researchers have developed COMPASS, a novel framework designed to enhance multimodal sensing by addressing the challenge of missing data modalities. This system ensures a consistent fusion interface by using proxy token…
-
ClimAgent framework uses LLMs for autonomous climate science analysis
Researchers have developed ClimAgent, an autonomous framework designed to tackle complex climate science analysis tasks. This system integrates a unified tool-use environment with reasoning protocols to perform end-to-e…