104 citations · 106 across the 31 of their papers we have counts for
36 papers
Joint Class-Time Learning for Video Classification with Multi-Instance Partial-Label Learning
Lingyu Shen, Wei Tang, Fakhri Karray +1
Multi-instance partial-label learning (MIPL) addresses inexact supervision in both the instance and label spaces, which can be applied to video classification. However, bag-level l…
Tropical Reinforcement Learning
Arip Asadulaev, Aladin Djuhera, Karim Salta +3
Reinforcement learning for large language models typically maximizes expected return, adding up the probabilities of all successful trajectories. However, the classical sum formula…
SEES: A Self-Evolving Embodied System via Failure-Guided VLA Policy Adaptation
Ziwen Li, Hanlue Zhang, Zhenyang Ren +9
Recent vision-language-action (VLA) policies demonstrate promising generalization across diverse short-horizon tasks. However, they remain unreliable on long-horizon tasks, partly…
Branched Optimal Transport Amortization
Semyon Semenov, Viktor Kovalchuk, Meir Roketlishvili +4
Methods of Branched Optimal Transport (BOT) mimic the economy and efficiency of natural tree-like structures, such as those found in rivers and biological systems. These methods ar…
Scaling Multi-Agent Systems with Prospect-State Propagation
Zhimei Chen, Mu Chen, Fakhri Karray
Current LLM-based multi-agent systems (MAS) periodically compress intermediate states to reduce inference-time token consumption, thereby attempting to incorporate more agents. How…
Towards Robust Reinforcement Learning for Small-Scale Language Model Agents
Md Rezwanul Haque, Md. Milon Islam, Fakhri Karray
The alignment of Small Language Models (SLMs) in the 70--500M parameter range using reinforcement learning is often considered unstable, though the underlying failure mechanisms ha…
Multimodal Unlearning Across Vision, Language, Video, and Audio: Survey of Methods, Datasets, and Benchmarks
Nobin Sarwar, Shubhashis Roy Dipta, Zheyuan Liu +1
With the growing adoption of VLMs, DMs, LLMs, and AFMs, these multimodal foundation models can inadvertently encode sensitive, copyrighted, biased, or unsafe cross-modal associatio…
PAST-TIDE: Prototype-Anchored Statement Tuning with Topic-Invariant Normalization for Stance Detection
Md. Shakhoyat Rahman Shujon, MD Jahid Hasan Jim, Md. Milon Islam +2
We introduce PAST-TIDE, our stance detection system addressing both subtasks of the StanceNakba Shared Task at NakbaNLP@LREC-COLING 2026. The main idea is statement tuning. We rede…
Dual Advantage Fields
Alexey Zemtsov, Maxim Bobrin, Alexander Nikulin +5
Offline goal-conditioned reinforcement learning requires both long-horizon reachability estimates and local action comparisons. Dual goal representations provide value fields that…
NL-MambaXCT: Self-Supervised Nested-Learning Mamba for Nomex Honeycomb X-ray CT Defect Classification
Ghaleb Aldoboni, Lobna Nassar, Fakhri Karray +1
X-ray computed tomography (XCT) is widely used for non-destructive testing of Nomex honeycomb structures in aerospace manufacturing, but industrial inspection still relies heavily…
Convex Compositional Reasoning Models
Meir Roketlishvili, Semyon Semenov, Maksim Bobrin +7
Compositional energy-based models can generalize to larger combinatorial reasoning problems by reusing a learned factor energy across many local constraints. In our paper, we show…
In-Context Learning Operates as Concept Subspace Learning
Wei Tang, Xinyan Jiang, Fakhri Karray +1
Regression and Bayesian accounts of in-context learning (ICL) explain how demonstrations can induce predictors, while mechanistic analyses often identify compact activation directi…
CAST: Channel-Aware Spatial Transfer Learning with Pseudo-Image Radar for Sign Language Recognition
Md. Shakhoyat Rahman Shujon, Sheikh Md. Galib Mahim, Md. Milon Islam +4
We propose CAST, a dual-stream architecture that utilizes channel-aware spatial transfer learning for isolated sign language recognition addressing the challenges of magnitude-only…
Projected Gradient Unlearning for Text-to-Image Diffusion Models: Defending Against Concept Revival Attacks
Aljalila Aladawi, Mohammed Talha Alam, Fakhri Karray
Machine unlearning for text-to-image diffusion models aims to selectively remove undesirable concepts from pre-trained models without costly retraining. Current unlearning methods…
CodeMMR: Bridging Natural Language, Code, and Image for Unified Retrieval
Jiahui Geng, Qing Li, Fengyu Cai +1
Code search, framed as information retrieval (IR), underpins modern software engineering and increasingly powers retrieval-augmented generation (RAG), improving code discovery, reu…
VulnScout-C: A Lightweight Transformer for C Code Vulnerability Detection
Aymen Lassoued, Nacef Mbarek, Bechir Dardouri +3
Vulnerability detection in C programs is a critical challenge in software security. Although large language models (LLMs) achieve strong detection performance, their multi-billion-…
Zero-Shot Off-Policy Learning
Arip Asadulaev, Maksim Bobrin, Salem Lahlou +3
Off-policy learning methods seek to derive an optimal policy directly from a fixed dataset of prior interactions. This objective presents significant challenges, primarily due to t…
Latent Reasoning in TRMs is Secretly a Policy Improvement Operator
Arip Asadulaev, Rayan Banerjee, Fakhri Karray +1
Recently, small models with latent recursion have obtained promising results on complex reasoning tasks. These results are typically explained by the theory that such recursion inc…
Expert or not? assessing data quality in offline reinforcement learning
Arip Asadulaev, Fakhri Karray, Martin Takac
Offline reinforcement learning (RL) learns exclusively from static datasets, without further interaction with the environment. In practice, such datasets vary widely in quality, of…
Y-Shaped Generative Flows
Arip Asadulaev, Semyon Semenov, Abduragim Shtanchaev +3
Modern continuous-time generative models typically induce \emph{V-shaped} flows: each sample travels independently along a nearly straight trajectory from the prior to the data. Al…
A Signer-Invariant Conformer and Multi-Scale Fusion Transformer for Continuous Sign Language Recognition
Md Rezwanul Haque, Md. Milon Islam, S M Taslim Uddin Raju +1
Continuous Sign Language Recognition (CSLR) faces multiple challenges, including significant inter-signer variability and poor generalization to novel sentence structures. Traditio…
FusionEnsemble-Net: An Attention-Based Ensemble of Spatiotemporal Networks for Multimodal Sign Language Recognition
Md. Milon Islam, Md Rezwanul Haque, S M Taslim Uddin Raju +1
Accurate recognition of sign language in healthcare communication poses a significant challenge, requiring frameworks that can accurately interpret complex multimodal gestures. To…
MDD-Net: Multimodal Depression Detection through Mutual Transformer
Md Rezwanul Haque, Md. Milon Islam, S M Taslim Uddin Raju +3
Depression is a major mental health condition that severely impacts the emotional and physical well-being of individuals. The simple nature of data collection from social media pla…
MMFformer: Multimodal Fusion Transformer Network for Depression Detection
Md Rezwanul Haque, Md. Milon Islam, S M Taslim Uddin Raju +3
Depression is a serious mental health illness that significantly affects an individual's well-being and quality of life, making early detection crucial for adequate care and treatm…