8 papers · 1 filter
RoPE Distinguishes Neither Positions Nor Tokens in Long Contexts, Provably
Yufeng Du, Phillip Harris, Minyang Tian +5
We identify intrinsic limitations of Rotary Positional Embeddings (RoPE) in Transformer-based long-context language models. Our theoretical analysis abstracts away from the specifi…
Compress, Gather, and Recompute: REFORMing Long-Context Processing in Transformers
Woomin Song, Sai Muralidhar Jayanthi, Srikanth Ronanki +5
As large language models increasingly gain popularity in real-world applications, processing extremely long contexts, often exceeding the model's pre-trained context limits, has em…
LAWCAT: Efficient Distillation from Quadratic to Linear Attention with Convolution across Tokens for Long Context Modeling
Zeyu Liu, Souvik Kundu, Lianghao Jiang +5
Although transformer architectures have achieved state-of-the-art performance across diverse domains, their quadratic computational complexity with respect to sequence length remai…
Context Length Alone Hurts LLM Performance Despite Perfect Retrieval
Yufeng Du, Minyang Tian, Srikanth Ronanki +7
Large language models (LLMs) often fail to scale their performance on long-context tasks performance in line with the context lengths they support. This gap is commonly attributed…
SpeechVerse: A Large-scale Generalizable Audio Language Model
Nilaksh Das, Saket Dingliwal, Srikanth Ronanki +14
Large language models (LLMs) have shown incredible proficiency in performing tasks that require semantic understanding of natural language instructions. Recently, many works have f…
Zero-resource Speech Translation and Recognition with LLMs
Karel Mundnich, Xing Niu, Prashant Mathur +10
Despite recent advancements in speech processing, zero-resource speech translation (ST) and automatic speech recognition (ASR) remain challenging problems. In this work, we propose…