8 citations · 18 across the 15 of their papers we have counts for
16 papers
RoleQ: Role-Aligned Scales for Converting Language Models to Ternary
Johannes Knittel, Alec Helbling, Hanspeter Pfister
Weight quantization below four bits shrinks memory and bandwidth at a perplexity that looks acceptable, but often at the cost of factual knowledge and task accuracy. Ternary weight…
Sparse Inter-Layer Dependencies of Transformer FFN Neurons
Johannes Knittel, Hanspeter Pfister
Feedforward network (FFN) blocks account for a large fraction of the parameters and computation in Transformer architectures, yet their internal structure remains difficult to inte…
Bias at the End of the Score
Salma Abdel Magid, Grace Guo, Esin Tureci +4
Reward models (RMs) are inherently non-neutral value functions designed and trained to encode specific objectives, such as human preferences or text-image alignment. RMs have becom…
A Rigorous Behavior Assessment of CNNs Using a Data-Domain Sampling Regime
Shuning Jiang, Wei-Lun Chao, Daniel Haehn +2
We present a data-domain sampling regime for quantifying CNNs' graphic perception behaviors. This regime lets us evaluate CNNs' ratio estimation ability in bar charts from three pe…
Beyond Linear Steering: Unified Multi-Attribute Control for Language Models
Narmeen Oozeer, Luke Marks, Shreyans Jain +2
Controlling multiple behavioral attributes in large language models (LLMs) at inference time is a challenging problem due to interference between attributes and the limitations of…
Enhancing User Performance and Human Factors through Visual Guidance in AR Assembly Tasks
Leon Pietschmann, Michel Schimpf, Zhu-Tian Chen +2
This study investigates the influence of Visual Guidance (VG) on user performance and human factors within Augmented Reality (AR) via a between-subjects experiment. VG is a crucial…
GPT-2 Through the Lens of Vector Symbolic Architectures
Johannes Knittel, Tushaar Gangavarapu, Hendrik Strobelt +1
Understanding the general priniciples behind transformer models remains a complex endeavor. Experiments with probing and disentangling features using sparse autoencoders (SAE) sugg…
Understanding Graphical Perception in Data Visualization through Zero-shot Prompting of Vision-Language Models
Grace Guo, Jenna Jiayi Kang, Raj Sanjay Shah +2
Vision Language Models (VLMs) have been successful at many chart comprehension tasks that require attending to both the images of charts and their accompanying textual descriptions…
Task-Specific Directions: Definition, Exploration, and Utilization in Parameter Efficient Fine-Tuning
Chongjie Si, Zhiyi Shi, Shifan Zhang +3
Large language models demonstrate impressive performance on downstream tasks, yet they require extensive resource consumption when fully fine-tuning all parameters. To mitigate thi…
They're All Doctors: Synthesizing Diverse Counterfactuals to Mitigate Associative Bias
Salma Abdel Magid, Jui-Hsien Wang, Kushal Kafle +1
Vision Language Models (VLMs) such as CLIP are powerful models; however they can exhibit unwanted biases, making them less safe when deployed directly in applications such as text-…
Benchmarking Out-of-Distribution Generalization Capabilities of DNN-based Encoding Models for the Ventral Visual Cortex
Spandan Madan, Will Xiao, Mingran Cao +3
We characterized the generalization capabilities of DNN-based encoding models when predicting neuronal responses from the visual cortex. We collected \textit{MacaqueITBench}, a lar…
Measuring and Controlling Instruction (In)Stability in Language Model Dialogs
Kenneth Li, Tianle Liu, Naomi Bashkansky +4
System-prompting is a standard tool for customizing language-model chatbots, enabling them to follow a specific instruction. An implicit assumption in the use of system prompts is…
The Indoor-Training Effect: unexpected gains from distribution shifts in the transition function
Serena Bono, Spandan Madan, Ishaan Grover +4
Is it better to perform tennis training in a pristine indoor environment or a noisy outdoor one? To model this problem, here we investigate whether shifts in the transition probabi…
Unraveling the Temporal Dynamics of the Unet in Diffusion Models
Vidya Prasad, Chen Zhu-Tian, Anna Vilanova +3
Diffusion models have garnered significant attention since they can effectively learn complex multivariate Gaussian distributions, resulting in diverse, high-quality outcomes. They…
LangSplat: 3D Language Gaussian Splatting
Minghan Qin, Wanhua Li, Jiawei Zhou +2
Humans live in a 3D world and commonly use natural language to interact with a 3D scene. Modeling a 3D language field to support open-ended language queries in 3D has gained increa…
Can Machines Imitate Humans? Integrative Turing-like tests for Language and Vision Demonstrate a Narrowing Gap
Mengmi Zhang, Elisa Pavarino, Xiao Liu +20
As AI becomes increasingly embedded in daily life, ascertaining whether an agent is human is critical. We systematically benchmark AI's ability to imitate humans in three language…