16 citations · 17 across the 7 of their papers we have counts for
8 papers
REAL: Benchmarking Autonomous Agents on Deterministic Simulations of Real Websites
Divyansh Garg, Shaun VanWeelden, Diego Caples +15
We introduce REAL, a benchmark and framework for multi-turn agent evaluations on deterministic simulations of real-world websites. REAL comprises high-fidelity, deterministic repli…
Unelicitable Backdoors in Language Models via Cryptographic Transformer Circuits
Andis Draguns, Andrew Gritsevskiy, Sumeet Ramesh Motwani +3
The rapid proliferation of open-source language models significantly increases the risks of downstream backdoor attacks. These backdoors can introduce dangerous behaviours during m…
Limitations of Agents Simulated by Predictive Models
Raymond Douglas, Jacek Karwowski, Chan Bae +2
There is increasing focus on adapting predictive models into agent-like systems, most notably AI assistants based on language models. We outline two structural reasons for why thes…
Mitigating the Influence of Distractor Tasks in LMs with Prior-Aware Decoding
Raymond Douglas, Andis Draguns, Tomáš Gavenčiak
The broad capabilities of Language Models (LMs) can be limited by their sensitivity to distractor tasks: LMs can infer secondary tasks from the prompt in addition to the intended o…
Unsupervised Training for Neural TSP Solver
Elīza Gaile, Andis Draguns, Emīls Ozoliņš +1
There has been a growing number of machine learning methods for approximately solving the travelling salesman problem. However, these methods often require solved instances for tra…
Gates Are Not What You Need in RNNs
Ronalds Zakovskis, Andis Draguns, Eliza Gaile +2
Recurrent neural networks have flourished in many areas. Consequently, we can see new RNN cells being developed continuously, usually by creating or using gates in a new, original…
Goal-Aware Neural SAT Solver
Emils Ozolins, Karlis Freivalds, Andis Draguns +3
Modern neural networks obtain information about the problem and calculate the output solely from the input values. We argue that it is not always optimal, and the network's perform…
Residual Shuffle-Exchange Networks for Fast Processing of Long Sequences
Andis Draguns, Emīls Ozoliņš, Agris Šostaks +2
Attention is a commonly used mechanism in sequence processing, but it is of O(n^2) complexity which prevents its application to long sequences. The recently introduced neural Shuff…