arxiv:2601.05242
Pavlo Molchanov PRO
pmolchanov
AI & ML interests
Efficiency in Multi-Modal LLMs
Recent Activity
upvoted a paper about 23 hours ago
SPEED-Bench: A Unified and Diverse Benchmark for Speculative Decoding liked a model about 1 month ago
mlx-community/Nemotron-Labs-Diffusion-3B-4bit upvoted an article about 1 month ago
Towards Speed-of-Light Text Generation with Nemotron-Labs Diffusion Language ModelsOrganizations
arxiv:2512.20856
arxiv:2512.20848
arxiv:2512.14067
arxiv:2511.21689
arxiv:2511.18890
arxiv:2511.16664
arxiv:2511.08923
arxiv:2511.03929
arxiv:2511.00088
arxiv:2510.18941
arxiv:2510.15870
arxiv:2510.15110
arxiv:2510.01180
arxiv:2509.26328
arxiv:2509.13317
arxiv:2509.00244
arxiv:2508.14444
arxiv:2507.12507
arxiv:2507.14204
arxiv:2507.07966
arxiv:2506.04174
arxiv:2506.02153
arxiv:2506.15702
arxiv:2504.16053
arxiv:2504.13161
arxiv:2504.11409
arxiv:2504.03624
arxiv:2503.19903
arxiv:2502.16025
arxiv:2412.11006
arxiv:2412.07679
arxiv:2412.04468
arxiv:2411.13676
arxiv:2411.12915
arxiv:2410.21271
arxiv:2410.01680
arxiv:2409.17481
arxiv:2408.11796
arxiv:2408.10188
arxiv:2407.17453
arxiv:2407.14679
arxiv:2406.10260
arxiv:2405.19335
arxiv:2403.19046
arxiv:2402.09353
arxiv:2312.07533
arxiv:2312.06709
arxiv:2306.14306
arxiv:2306.06189
arxiv:2212.03237
arxiv:2206.09959
arxiv:2110.04869
