Africa
SequentialAttention+ + for Block Sparsification: Differentiable Pruning Meets Combinatorial Optimization
Pruning methods for neural networks [LeCun et al., 1989] replace dense weight matrices by sparse
Efficient Leverage Score Sampling for Tensor Train Decomposition
In this paper, we propose an efficient algorithm to accelerate computing the TT decomposition with the Alternating Least Squares (ALS) algorithm relying on exact leverage scores sampling.
Secret Collusion among AI Agents: Multi-Agent Deception via Steganography
We revisit this scenario as an experimental case study in Section 6.
Dissecting the Interplay of Attention Paths in a Statistical Mechanics Theory of Transformers Lorenzo Tiberi 1,2 Francesca Mignacco
Second, generalization--what specific aspects of the transformer architecture are responsible for their effective learning?
Scissorhands: Exploiting the Persistence of Importance Hypothesis for LLM KV Cache Compression at Test Time
Large language models(LLMs) have sparked a new wave of exciting AI applications. Hosting these models at scale requires significant memory resources.