We have 4 of 92 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.
The large KV-cache size of modern LLMs creates a barrier to efficient deployment. Recent work has explored replacing attention layers'RoPE positional embeddings with alternative decay-based mechanisms, which can then be used to prune KV-cache during inference. However, these decay functions have limited expressivity, a...
DIALER is designed, a system that exploits the spare compute cycles freed by retraining-free VFM inference to mitigate rare-class misclassifications and improves rare-class accuracy by up to 14.0% without interfering with real-time VFM inference for multi-stream analytics.
Evaluating state-of-the-art video generators, image generators, and LLM/VLM baselines reveals a sharp gap between visual quality and reasoning correctness: video models perform best on Physical Commonsense, but remain weak on symbolic tasks such as Sudoku, ARC, and Math, and brittle in cross-view embodied navigation.
Block-diffusion drafters like dFlash generate an entire block of draft tokens in a single forward pass, drastically reducing the overhead of multiple-token drafting in speculative decoding. The crucial final step of the single-pass discrete denoising process involves using the logit distribution at each position to sam...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
