21 accepted papers
Large language models exhibit systematic vulnerabilities to adversarial attacks despite extensive safety alignment through supervised fine-tuning and reinforcement learning from human feedback. These vulnerabilities manifest as differential safety behavior across token positions, with safety modific
Modern deep-learning models have achieved remarkable success in time-series forecasting. Yet, their performance degrades in long-term prediction due to error accumulation in autoregressive inference, where predictions are recursively used as inputs. While classical error correction mechanisms (ECMs)…
Designing effective strategies for controlling epidemic spread by vaccination is an important question in epidemiology, especially in the early stages when vaccines are limited. This is a challenging question when the contact network is very heterogeneous, and strategies based on controlling network…
Medical Large Multi-modal Models (LMMs) have demonstrated remarkable capabilities in medical data interpretation. However, these models frequently generate hallucinations contradicting source evidence, particularly due to inadequate localization reasoning. This work reveals a critical limitation in
How can Large Language Models (LLMs) be aligned with human intentions and values? A typical solution is to gather human preference on model outputs and finetune the LLMs accordingly while ensuring that updates do not deviate too far from a reference model. Recent approaches, such as direct preferenc…
Artificial agents with the aid of large language models (LLMs) are effective in various real-world scenarios but struggle to cooperate in social dilemmas. When making decisions under the strain of selecting between long-term consequences and short-term benefits in commonly shared resources, LLM-base
Effective decision-making in partially observable environments demands robust memory management. Despite their success in supervised learning, current deep-learning memory models struggle in reinforcement learning environments that are partially observable and long-term. They fail to efficiently cap…
Metrics such as the outbreak size in an epidemic process on a network are fundamental quantities used in public health analyses. The datasets used in such models used in practice, e.g., the contact network and disease states, are sensitive in many settings. We study the complexity of computing epide…
Stochastic block models (SBMs) are a very commonly studied network model for community detection algorithms. In the standard form of an SBM, the $n$ vertices (or nodes) of a graph are generally divided into multiple pre-determined communities (or clusters). Connections between pairs of vertices are…
The challenge in constructing artificial social agents is to enable adaptation ability to novel agents, and is called zero-shot coordination (ZSC). A promising approach is to train the adaptive agents by interacting with a diverse pool of collaborators, assuming that the greater the diversity in oth…
Set Cover is a fundamental problem in combinatorial optimization which has been studied for many decades due to its various applications across multiple domains. In many of these domains, the input data consists of locations, relationships, and other sensitive information of individuals which may le…
One of the most common problems studied in the context of differential privacy for graph data is counting the number of non-induced embeddings of a subgraph in a given graph. These counts have very high global sensitivity. Therefore, adding noise based on powerful alternative techniques, such as sm…
Social reasoning necessitates the capacity of theory of mind (ToM), the ability to contextualise and attribute mental states to others without having access to their internal cognitive structure. Recent machine learning approaches to ToM have demonstrated that we can train the observer to read the p…
Understanding other agents is a key challenge in constructing artificial social agents. Current works focus on centralised training, wherein agents are allowed to know all the information about others and the environmental state during training. In contrast, this work studies decentralised training,…
The goal of community detection over graphs is to recover underlying labels/attributes of users (e.g., political affiliation) given the connectivity between users. There has been significant recent progress on understanding the fundamental limits of community detection when the graph is generated fr…
We introduce a novel training procedure for policy gradient methods wherein episodic memory is used to optimize the hyperparameters of reinforcement learning algorithms on-the-fly. Unlike other hyperparameter searches, we formulate hyperparameter scheduling as a standard Markov Decision Process and…
We introduce a constrained optimization method for policy gradient reinforcement learning, which uses two trust regions to regulate each policy update. In addition to using the proximity of one single old policy as the first trust region as done by prior works, we propose forming a second trust regi…
Data-free Knowledge Distillation (DFKD) has attracted attention recently thanks to its appealing capability of transferring knowledge from a teacher network to a student network without using training data. The main idea is to use a generator to synthesize data for training the student. As the gener…
"Trojan attacks on deep neural networks are both dangerous and surreptitious. Over the past few years, Trojan attacks have advanced from using only a single input-agnostic trigger and targeting only one class to using multiple, input-specific triggers and targeting multiple classes. However, Trojan…
Densest subgraph detection is a fundamental graph mining problem, with a large number of applications. There has been a lot of work on efficient algorithms for finding the densest subgraph in massive networks. However, in many domains, the network is private, and returning a densest subgraph can rev…
Motion planning with predictable timing and velocity will enable a number of interesting applications such as autonomous intersection management (AIM). These planning algorithms depend on an accurate model of the performance of the vehicular controllers, which can be highly non-linear. Au et al. pro…