10 accepted papers
Loss spikes remain a persistent obstacle in large-scale language model pretraining. While previous research has attempted to identify the root cause of loss spikes by investigating individual factors, we observe that, in practice, such spikes are typically triggered by the confluence of heterogeneou…
Document parsing is a fine-grained task where image resolution significantly impacts performance. While advanced research leveraging vision-language models benefits from high-resolution input to boost model performance, this often leads to a quadratic increase in the number of vision tokens and sign
Autoregressive decoding of large language models is frequently memory-traffic bound, so ultra-low-bit weight-only PTQ helps only if dequantization avoids irregular codebook or LUT access in the inner loop. Under the GPU-friendly bitshift trellis, existing 2-bit trellis-coded quantization (TCQ) pipel…
The computational and memory demands of vanilla attention scale quadratically with the sequence length $N$, posing significant challenges for processing long sequences in Transformer models. FlashAttention alleviates these challenges by eliminating the $\mathcal{O}(N^2)$ memory dependency and reduci…
Large Language Models (LLMs) have ignited an innovative surge of AI applications, marking a new era of exciting possibilities equipped with extended context windows. However, hosting these models is cost-prohibitive mainly due to the extensive memory consumption of KV Cache involving long-context mo…
PaddleSpeech is an open-source all-in-one speech toolkit. It aims at facilitating the development and research of speech processing technologies by providing an easy-to-use command-line interface and a simple code structure. This paper describes the design philosophy and core architecture of PaddleS…
Relational graph neural networks have garnered particular attention to encode graph context in knowledge graphs (KGs). Although they achieved competitive performance on small KGs, how to efficiently and effectively utilize graph context for large KGs remains an open problem. To this end, we propose…
Sparsely gated Mixture-of-Expert (MoE) has demonstrated its effectiveness in scaling up deep neural networks to an extreme scale. Despite that numerous efforts have been made to improve the performance of MoE from the model design or system optimization perspective, existing MoE dispatch patterns ar…
The main challenge of cross-modal retrieval is to learn the consistent embedding for heterogeneous modalities. To solve this problem, traditional label-wise cross-modal approaches usually constrain the inter-modal and intra-modal embedding consistency relying on the label ground-truths. However, the…
To represent a text as a bag of properly identified “phrases” and use the representation for processing the text is proved to be useful. The key question here is how to identify the phrases and represent them. The traditional method of utilizing n-grams can be regarded as an approximation of the app…