· ai
[Paper] Low-Rank Key Value Attention
Transformer pretraining is increasingly constrained by memory and compute requirements, with the key-value (KV) cache emerging as a dominant bottleneck during t...
-
- · ai
[Paper] Exploring LLM Features in Predictive Process Monitoring for Small-Scale Event-Logs
Predictive Process Monitoring is a branch of process mining that aims to predict the outcome of an ongoing process. Recently, it leveraged machine-and-deep lear...
- · ai
[Paper] MHA2MLA-VLM: Enabling DeepSeek's Economical Multi-Head Latent Attention across Vision-Language Models
As vision-language models (VLMs) tackle increasingly complex and multimodal tasks, the rapid growth of Key-Value (KV) cache imposes significant memory and compu...
- · ai
[Paper] Learning Semantic-Geometric Task Graph-Representations from Human Demonstrations
Learning structured task representations from human demonstrations is essential for understanding long-horizon manipulation behaviors, particularly in bimanual ...
- · ai
[Paper] Interactive Narrative Analytics: Bridging Computational Narrative Extraction and Human Sensemaking
Information overload and misinformation create significant challenges in extracting meaningful narratives from large news collections. This paper defines the na...
- · ai
[Paper] PRISM-CAFO: Prior-conditioned Remote-sensing Infrastructure Segmentation and Mapping for CAFOs
Large-scale livestock operations pose significant risks to human health and the environment, while also being vulnerable to threats such as infectious diseases ...
- · ai
[Paper] When Are Two Scores Better Than One? Investigating Ensembles of Diffusion Models
Diffusion models now generate high-quality, diverse samples, with an increasing focus on more powerful models. Although ensembling is a well-known way to improv...
- · ai
[Paper] Predict the Retrieval! Test time adaptation for Retrieval Augmented Generation
Retrieval-Augmented Generation (RAG) has emerged as a powerful approach for enhancing large language models' question-answering capabilities through the integra...
- · ai
[Paper] Map2Thought: Explicit 3D Spatial Reasoning via Metric Cognitive Maps
We propose Map2Thought, a framework that enables explicit and interpretable spatial reasoning for 3D VLMs. The framework is grounded in two key components: Metr...
- · ai
[Paper] Hierarchical Orthogonal Residual Spread for Precise Massive Editing in Large Language Models
Large language models (LLMs) exhibit exceptional performance across various domains, yet they face critical safety concerns. Model editing has emerged as an eff...
- · ai
[Paper] The unreasonable effectiveness of pattern matching
We report on an astonishing ability of large language models (LLMs) to make sense of 'Jabberwocky' language in which most or all content words have been randoml...
- · ai
[Paper] PubMed-OCR: PMC Open Access OCR Annotations
PubMed-OCR is an OCR-centric corpus of scientific articles derived from PubMed Central Open Access PDFs. Each page image is annotated with Google Cloud Vision a...