1 citations · 2 across the 11 of their papers we have counts for
11 papers
The Count Is There, but Misaligned: Understanding and Correcting Counting Failures in VLMs
Ahmed Oumar El-Shangiti, Abzal Nurgazy, Hilal AlQuabeh +2
Despite strong performance on many multimodal tasks, vision-language models (VLMs) still struggle with basic object counting. We investigate whether this reflects missing internal…
The FIL Hypothesis: Inductive Biases Help with Kernel Engineering
Nikolai Rozanov, Subhabrata Dutta, Preslav Nakov +1
The Bitter Lesson, which posits that general-purpose methods that scale with computation and data ultimately outperform those with built-in human knowledge, has become a dominant p…
ThinkBooster: A Unified Framework for Seamless Test-Time Scaling of LLM Reasoning
Vladislav Smirnov, Chieu Nguyen, Sergey Senichev +14
Test-time compute (TTC) scaling has emerged as a powerful paradigm for improving large language model (LLM) reasoning by allocating additional compute during inference, e.g., via m…
Fine-tuning with RAG for Improving LLM Learning of New Skills
Humaid Ibrahim, Nikolai Rozanov, Marek Rei
Large language model (LLM) agents deployed for multi-step tasks frequently fail in predictable ways: attempting actions with unmet preconditions, issuing redundant commands, or mis…
IsoChronoMeter: A simple and effective isochronic translation evaluation metric
Nikolai Rozanov, Vikentiy Pankov, Dmitrii Mukhutdinov +1
Machine translation (MT) has come a long way and is readily employed in production systems to serve millions of users daily. With the recent advances in generative AI, a new form o…
StateAct: Enhancing LLM Base Agents via Self-prompting and State-tracking
Nikolai Rozanov, Marek Rei
Large language models (LLMs) are increasingly used as autonomous agents, tackling tasks from robotics to web navigation. Their performance depends on the underlying base agent. Exi…
Efficient Exploration in Deep Reinforcement Learning: A Novel Bayesian Actor-Critic Algorithm
Nikolai Rozanov
Reinforcement learning (RL) and Deep Reinforcement Learning (DRL), in particular, have the potential to disrupt and are already changing the way we interact with the world. One of…
Learning From Free-Text Human Feedback -- Collect New Datasets Or Extend Existing Ones?
Dominic Petrak, Nafise Sadat Moosavi, Ye Tian +2
Learning from free-text human feedback is essential for dialog systems, but annotated data is scarce and usually covers only a small fraction of error types known in conversational…
Common Sense or World Knowledge? Investigating Adapter-Based Knowledge Injection into Pretrained Transformers
Anne Lauscher, Olga Majewska, Leonardo F. R. Ribeiro +3
Following the major success of neural language models (LMs) such as BERT or GPT-2 on a variety of language understanding tasks, recent work focused on injecting (structured) knowle…
LIDA: Lightweight Interactive Dialogue Annotator
Edward Collins, Nikolai Rozanov, Bingbing Zhang
Dialogue systems have the potential to change how people interact with machines but are highly dependent on the quality of the data used to train them. It is therefore important to…
Evolutionary Data Measures: Understanding the Difficulty of Text Classification Tasks
Edward Collins, Nikolai Rozanov, Bingbing Zhang
Classification tasks are usually analysed and improved through new model architectures or hyperparameter optimisation but the underlying properties of datasets are discovered on an…