Researchers from Srikar Kashyap Pulipapa's team submitted a system to the WMT 2026 Multilingual Instruction Shared Task. Their approach uses a pre-tra...
A new AI model called Fuzzy-MoE has been proposed for forecasting non-stationary multivariate time series. Unlike existing models that compress differ...
Researchers have developed a tool called CARD that helps diagnose problems in how vision-language models (VLMs) use internal representations of mental...
Researchers have found that speech models (SpeechLMs) can be contaminated by their own previous beliefs when interpreting audio streams. This 'previou...
Researchers have developed CertVLA, a defense mechanism to protect Vision-Language-Action (VLA) models from physical visual attacks. These attacks inv...
Researchers have proposed a framework called CAIRO to improve Large Language Model (LLM) recommenders. CAIRO structures and selects relevant item meta...
Researchers have proposed a new framework called FreqDiff for predicting future facts in temporal knowledge graphs. This approach uses denoising and s...
A new AI framework called TRACE is proposed for breast ultrasound diagnosis. It uses structured radiology reports to guide the training process and en...
Researchers have developed a method to improve the performance of AI-generated images in terms of both visual fidelity and query retrieval. The approa...
Researchers have investigated the performance of Muon, a matrix-aware optimizer for large models. They found that while Muon improves training efficie...
Researchers have proposed a new method called STAR-OPD to improve the performance of aspect-based sentiment analysis (ABSA) quadruple extraction. This...
Researchers have developed a new method for controlling the magnetic configuration in an experimental setup called EXL-50U. The goal is to manage heat...