Related papers: Regular Expression Denial of Service Induced by Ba…

Large Language Model-based agents(LLM-based agents) are increasingly deployed in customer service, yet they often forget across sessions, repeat errors, and lack mechanisms for continual self-improvement. This makes them unreliable in…

We present the first rigorous security, performance, energy, and cost analyses of the state-of-the-art on-DRAM-die read disturbance mitigation method, Per Row Activation Counting (PRAC), described in JEDEC DDR5 specification's April 2024…

Predictive process monitoring (PPM) focuses on predicting future process trajectories, including next activity predictions. This is crucial in dynamic environments where processes change or face uncertainty. However, current frameworks…

Test-time inference has emerged as a powerful paradigm for enabling language models to ``think'' longer and more carefully about complex challenges, much like skilled human experts. While reinforcement learning (RL) can drive…

Recursive self-improvement--where a model iteratively trains on its own outputs--promises sustained capability growth but faces a fundamental obstacle: recursive drift. As models train on self-generated data across multiple iterations,…

Refusal on harmful prompts is a key safety behaviour in instruction-tuned large language models (LLMs), yet the internal causes of this behaviour remain poorly understood. We study two public instruction-tuned models, Gemma-2-2B-IT and…

Autoregressive language models (ARMs) suffer from the reversal curse: after learning ''$A$ is $B$,'' they often fail on the reverse query ''$B$ is $A$.'' Masked diffusion language models (MDMs) exhibit this failure in a much weaker form,…

Recurrent Neural Networks (RNNs) have shown great success in modeling time-dependent patterns, but there is limited research on their learned representations of latent temporal features and the emergence of these representations during…

This paper investigates the threat of backdoors in Deep Reinforcement Learning (DRL) agent policies and proposes a novel method for their detection at runtime. Our study focuses on elusive in-distribution backdoor triggers. Such triggers…

Adapting large language models (LLMs) via reinforcement learning (RL) is often bottlenecked by the generation stage, which can consume over 75\% of the training time. Speculative decoding (SD) accelerates autoregressive generation in…

Large Language Models (LLMs) can acquire deceptive behaviors through backdoor attacks, where the model executes prohibited actions whenever secret triggers appear in the input. Existing safety training methods largely fail to address this…

Feedback-driven recurrent spiking neural networks (RSNNs) are powerful computational models that can mimic dynamical systems. However, the presence of a feedback loop from the readout to the recurrent layer de-stabilizes the learning…

Speculative execution is an optimization technique that has been part of CPUs for over a decade. It predicts the outcome and target of branch instructions to avoid stalling the execution pipeline. However, until recently, the security…

Nearly all real world tasks are inherently partially observable, necessitating the use of memory in Reinforcement Learning (RL). Most model-free approaches summarize the trajectory into a latent Markov state using memory models borrowed…

Modern machine learning increasingly requires training on a large collection of data from multiple sources, not all of which can be trusted. A particularly concerning scenario is when a small fraction of poisoned data changes the behavior…

One common belief is that with complex models and pre-training on large-scale datasets, transformer-based methods for referring expression comprehension (REC) perform much better than existing graph-based methods. We observe that since most…

Large Reasoning Models (LRMs) employ reasoning to address complex tasks. Such explicit reasoning requires extended context lengths, resulting in substantially higher resource consumption. Prior work has shown that adversarially crafted…

Deep reinforcement learning (RL) has achieved remarkable success in solving complex tasks through its integration with deep neural networks (DNNs) as function approximators. However, the reliance on DNNs has introduced a new challenge…

Residual reinforcement learning (RL) enables stable online refinement of expressive pretrained policies by freezing the base and learning only bounded corrections. However, value learning in residual RL poses unique challenges that remain…

To combat adversarial spelling mistakes, we propose placing a word recognition model in front of the downstream classifier. Our word recognition models build upon the RNN semi-character architecture, introducing several new backoff…