Search Results for author:
Found 18 papers, 14 papers with code
FaithEval: Can Your Language Model Stay Faithful to Context, Even If "The Moon is Made of Marshmallows"
Ensuring faithfulness to context in large language models (LLMs) and retrieval-augmented generation (RAG) systems is crucial for reliable deployment in real-world applications, as incorrect or unsupported information can erode user trust.
Discovering the Gems in Early Layers: Accelerating Long-Context LLMs with 1000x Input Token Reduction
Our research introduces a novel approach for the long context bottleneck to accelerate LLM inference and reduce GPU memory consumption.
SFR-RAG: Towards Contextually Faithful LLMs
Retrieval Augmented Generation (RAG), a paradigm that integrates external contextual information with large language models (LLMs) to enhance factual accuracy and relevance, has emerged as a pivotal area in generative AI.
Is A Picture Worth A Thousand Words? Delving Into Spatial Reasoning for Vision Language Models
Large language models (LLMs) and vision-language models (VLMs) have demonstrated remarkable performance across a wide range of tasks and domains.
Understanding Retrieval-Augmented Task Adaptation for Vision-Language Models
Pre-trained contrastive vision-language models have demonstrated remarkable performance across a wide range of tasks.
Unsolvable Problem Detection: Evaluating Trustworthiness of Vision Language Models
This paper introduces a novel and significant challenge for Vision Language Models (VLMs), termed Unsolvable Problem Detection (UPD).
HYPO: Hyperspherical Out-of-Distribution Generalization
Out-of-distribution (OOD) generalization is critical for machine learning models deployed in the real world.
How Does Fine-Tuning Impact Out-of-Distribution Detection for Vision-Language Models?
Recent CLIP-based fine-tuning methods such as prompt learning have demonstrated significant improvements in ID classification and OOD generalization where OOD labels are available.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
Domain Generalization via Nuclear Norm Regularization
In this paper, we propose a simple and effective regularization method based on the nuclear norm of the learned features for domain generalization.
Delving into Out-of-Distribution Detection with Vision-Language Representations
Recognizing out-of-distribution (OOD) samples is critical for machine learning systems deployed in the open world.
POEM: Out-of-Distribution Detection with Posterior Sampling
In this work, we propose a novel posterior sampling-based outlier mining framework, POEM, which facilitates efficient use of outlier data and promotes learning a compact decision boundary between ID and OOD data for improved detection.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
Utilizing Language-Image Pretraining for Efficient and Robust Bilingual Word Alignment
Word translation without parallel corpora has become feasible, rivaling the performance of supervised methods.
Out-of-Distribution Detection with Deep Nearest Neighbors
In this paper, we explore the efficacy of non-parametric nearest-neighbor distance for OOD detection, which has been largely overlooked in the literature.
Are Vision Transformers Robust to Spurious Correlations?
Deep neural networks may be susceptible to learning spurious correlations that hold on average but not in atypical test samples.
How to Exploit Hyperspherical Embeddings for Out-of-Distribution Detection?
Out-of-distribution (OOD) detection is a critical task for reliable machine learning.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
+1
On the Impact of Spurious Correlation for Out-of-distribution Detection
Modern neural networks can assign high confidence to inputs drawn from outside the training distribution, posing threats to models in real-world deployments.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
Model-based Reinforcement Learning for Continuous Control with Posterior Sampling
In this paper, we study model-based posterior sampling for reinforcement learning (PSRL) in continuous state-action spaces theoretically and empirically.
Efficient Exploration for Model-based Reinforcement Learning with Continuous States and Actions
Our bound can be extended to nonlinear cases as well: using linear kernels on the feature representation $\phi$, the Bayesian regret bound becomes $\tilde{O}(H^{3/2}d_{\phi}\sqrt{T})$, where $d_\phi$ is the dimension of the representation space.
