Search Results for author:
Found 9 papers, 3 papers with code
Building A Proof-Oriented Programmer That Is 64% Better Than GPT-4o Under Data Scarsity
Existing LMs struggle with proof-oriented programming due to data scarcity, which manifest in two key ways: (1) a lack of sufficient corpora for proof-oriented programming languages such as F*, and (2) the absence of large-scale, project-level proof-oriented implementations that can teach the model the intricate reasoning process when performing proof-oriented programming.
AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents
The robustness of LLMs to jailbreak attacks, where users design prompts to circumvent safety measures and misuse model capabilities, has been studied primarily for LLMs acting as simple chatbots.
$\textbf{Only-IF}$:Revealing the Decisive Effect of Instruction Diversity on Generalization
In both cases, we demonstrate that 1) better performance can be achieved by increasing the diversity of an established dataset while keeping the data size constant, and 2) when scaling up the data, diversifying the semantics of instructions is more effective than simply increasing the quantity of similar data.
MAGICS: Adversarial RL with Minimax Actors Guided by Implicit Critic Stackelberg for Convergent Neural Synthesis of Robot Safety
While robust optimal control theory provides a rigorous framework to compute robot control policies that are provably safe, it struggles to scale to high-dimensional problems, leading to increased use of deep learning for tractable synthesis of robot safety.
Tamper-Resistant Safeguards for Open-Weight LLMs
Rapid advances in the capabilities of large language models (LLMs) have raised widespread concerns regarding their potential for malicious use.
Improving Alignment and Robustness with Circuit Breakers
Existing techniques aimed at improving alignment, such as refusal training, are often bypassed.
From Symbolic Tasks to Code Generation: Diversification Yields Better Task Performers
Instruction tuning -- tuning large language models on instruction-output pairs -- is a promising technique for making models better adapted to the real world.
Instruction Diversity Drives Generalization To Unseen Tasks
We investigate the trade-off between the number of instructions the model is trained on and the number of training samples provided for each instruction and observe that the diversity of the instruction set determines generalization.
3D Pose Detection in Videos: Focusing on Occlusion
In this work, we build upon existing methods for occlusion-aware 3D pose detection in videos.
