FLARE: Faithful Logic-Aided Reasoning and Exploration
We introduce Faithful Logic-Aided Reasoning and Exploration (FLARE), a novel interpretable approach for traversing the problem space using task decomp…
DeCoRe: Decoding by Contrasting Retrieval Heads to Mitigate Hallucinations
Large Language Models (LLMs) often hallucinate, producing unfaithful or factually incorrect outputs by misrepresenting the provided context. We propos…
Fast and Expressive Multi-Token Prediction with Probabilistic Circuits
Multi-token prediction (MTP) is a prominent strategy to significantly speed up generation in large language models (LLMs), especially in byte-level LLMs, which …
Neurosymbolic Diffusion Models
Neurosymbolic (NeSy) predictors combine neural perception with symbolic reasoning to solve tasks like visual reasoning. However, standard NeSy predict…
MMLongBench: Benchmarking Long-Context Vision-Language Models Effectively and Thoroughly
We introduce MMLongBench, the first benchmark covering a diverse set of long-context vision-language tasks to evaluate long-context vision-language mo…
Adaptive Layer and Token Selection for Efficient Fine-Tuning of Vision Transformers
Foundation models for computer vision built on Vision Transformer (ViT) architectures have become increasingly widespread. However, their fine-tuning process is resource-intensive, slowing …
Neurosymbolic Reasoning Shortcuts under the Independence Assumption
The ubiquitous independence assumption among symbolic concepts in neurosymbolic (NeSy) predictors is a convenient simplification that speeds up probab…
Universal Properties of Activation Sparsity in Modern Large Language Models
Activation sparsity is an intriguing property of deep neural networks that has been extensively studied in ReLU-based models, due to its advantages …
Fine-Tuning Foundation Models for Temporal Knowledge Graph Reasoning
Foundation models have recently demonstrated strong performance in various knowledge graph reasoning tasks. However, their applicability to temporal knowledge graphs (TKGs), where …