Search Results for author:
Found 14 papers, 2 papers with code
Semantic Specialization in MoE Appears with Scale: A Study of DeepSeek R1 Expert Specialization
DeepSeek-R1, the largest open-source Mixture-of-Experts (MoE) model, has demonstrated reasoning capabilities comparable to proprietary frontier models.
Steering Large Language Models to Evaluate and Amplify Creativity
Although capable of generating creative text, Large Language Models (LLMs) are poor judges of what constitutes "creativity".
Training-Free Mitigation of Language Reasoning Degradation After Multimodal Instruction Tuning
In this work, we explore the effects of multimodal instruction tuning on language reasoning performance.
Debias your Large Multi-Modal Model at Test-Time with Non-Contrastive Visual Attribute Steering
Large Multi-Modal Models (LMMs) have demonstrated impressive capabilities as general-purpose chatbots that can engage in conversations about a provided input, such as an image.
Debiasing Large Vision-Language Models by Ablating Protected Attribute Representations
Large Vision Language Models (LVLMs) such as LLaVA have demonstrated impressive capabilities as general-purpose chatbots that can engage in conversations about a provided input image.
A Domain-Agnostic Approach for Characterization of Lifelong Learning Systems
Despite the advancement of machine learning techniques in recent years, state-of-the-art systems lack robustness to "real world" events, where the input distributions and tasks encountered by the deployed systems will not be limited to the original training context, and systems will instead need to adapt to novel distributions and tasks while deployed.
Generalizing Cross Entropy Loss with a Beta Proper Composite Loss: An Improved Loss Function for Open Set Recognition
This Beta loss is a proper composite loss with a Beta weight function.
Contrastive Identification of Covariate Shift in Image Data
Identifying covariate shift is crucial for making machine learning systems robust in the real world and for detecting training data biases that are not reflected in test data.
Generative Particle Variational Inference via Estimation of Functional Gradients
Recently, particle-based variational inference (ParVI) methods have gained interest because they can avoid arbitrary parametric assumptions that are common in variational inference.
Avoiding Side Effects in Complex Environments
By preserving optimal value for a single randomly generated reward function, AUP incurs modest overhead while leading the agent to complete the specified task and avoid many side effects.
Implicit Generative Modeling for Efficient Exploration
Each random draw from our generative model is a neural network that instantiates the dynamic function, hence multiple draws would approximate the posterior, and the variance in the future prediction based on this posterior is used as an intrinsic reward for exploration.
HyperGAN: A Generative Model for Diverse, Performant Neural Networks
We introduce HyperGAN, a new generative model for learning a distribution of neural network parameters.
HyperGAN: Exploring the Manifold of Neural Networks
We introduce HyperGAN, a generative network that learns to generate all the weight parameters of deep neural networks.
Unifying Bilateral Filtering and Adversarial Training for Robust Neural Networks
To evaluate against an adversary with complete knowledge of our defense, we adapt the bilateral filter as a trainable layer in a neural network and show that adding this layer makes ImageNet images significantly more robust to attacks.
