19 papers
Do Robot Snakes Dream like Electric Sheep? Investigating the Effects of Architectural Inductive Biases on Hallucination
Jerry Huang, Prasanna Parthasarathi, Mehdi Rezagholizadeh +2
The growth in prominence of large language models (LLMs) in everyday life can be largely attributed to their generative abilities, yet some of this is also owed to the risks and co…
DTRNet: Dynamic Token Routing Network to Reduce Quadratic Costs in Transformers
Aman Sharma, Saeed Najafi, Parsa Farinneya +6
Transformers achieve state-of-the-art results across many tasks, but their uniform application of quadratic self-attention to every token at every layer makes them computationally…
ReGLA: Refining Gated Linear Attention
Peng Lu, Ivan Kobyzev, Mehdi Rezagholizadeh +2
Recent advancements in Large Language Models (LLMs) have set themselves apart with their exceptional performance in complex language modelling tasks. However, these models are also…
Batch-Max: Higher LLM Throughput using Larger Batch Sizes and KV Cache Compression
Michael R. Metel, Boxing Chen, Mehdi Rezagholizadeh
Several works have developed eviction policies to remove key-value (KV) pairs from the KV cache for more efficient inference. The focus has been on compressing the KV cache after t…
LABO: Towards Learning Optimal Label Regularization via Bi-level Optimization
Peng Lu, Ahmad Rashid, Ivan Kobyzev +2
Regularization techniques are crucial to improving the generalization performance and training efficiency of deep neural networks. Many deep learning algorithms rely on weight deca…
Balcony: A Lightweight Approach to Dynamic Inference of Generative Language Models
Benyamin Jamialahmadi, Parsa Kavehzadeh, Mehdi Rezagholizadeh +5
Deploying large language models (LLMs) in real-world applications is often hindered by strict computational and latency constraints. While dynamic inference offers the flexibility…