We have 3 of 10 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
Looped Transformers improve parameter efficiency by repeatedly applying shared Transformer blocks over multiple recurrent loops, increasing computational depth without increasing the parameter count. However, KV cache memory still scales with the number of loops, becoming a key memory bottleneck that limits batch size...
This work proposes LoopSpec, a training-free self-speculative decoding framework tailored for Looped Transformers that introduces a selective second proposal from deeper recurrent depth while ensuring lossless decoding under both greedy and sampling regimes.
Experiments show that HVA establishes a new Pareto frontier for training-free sparse attention in video diffusion, reducing end-to-end latency by up to $2.13\times while improving fidelity over existing training-free sparse attention baselines.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
