3 papers
cs.LG2026
DASC: Decay-Aware State Compression for Hybrid Linear-Attention Serving
Yanqi Yu, Pingwei Sun, Jianchao Tan +4
Hybrid linear-attention architectures have recently scaled to large open-weight models, offering quality competitive with full attention while substantially reducing key/value (KV)…
cs.LG2026
DAMP: Decay-Aware Mixed-Precision Recurrent-State Quantization
Tao Zhang, Jianchao Tan, Pingwei Sun +5
Softmax attention stores key and value vectors for every preceding token, causing inference memory to grow with sequence length. Recent language models incorporating Gated DeltaNet…
cs.CV2025
Crowdsource, Crawl, or Generate? Creating SEA-VL, a Multicultural Vision-Language Dataset for Southeast Asia
Samuel Cahyawijaya, Holy Lovenia, Joel Ruben Antony Moniz +89
Southeast Asia (SEA) is a region of extraordinary linguistic and cultural diversity, yet it remains significantly underrepresented in vision-language (VL) research. This often resu…