11 citations · 37 across the 35 of their papers we have counts for
11 papers · 1 filter
Differentiable Koopman Operator for Contrastive Learning on Dynamic Graphs
Md Abrar Jahin, Taufikur Rahman Fuad, Md Rizwan Parvez
Real-world interaction networks are inherently dynamic: edges form and dissolve as node behavior shifts over time. Most snapshot-based contrastive methods encode temporal dependenc…
AgentTell: Behavioural Side-Channel Leakage in Browser-Use Agents
Asif Shahriar, Md Nafiu Rahman, Sadif Ahmed +2
Browser-use agents often carry information in their context as they move between websites. While it may be necessary for task completion, it also creates a privacy risk, especially…
TAME: Token Attribution and Masking for Emergent misalignment
Md Rayhanul Masud, Md Rizwan Parvez
Fine-tuning an aligned language model on narrow, flawed data can induce harmful behavior far outside the training domain, known as emergent misalignment (EM). Prior work has locali…
QuantumQUBO Agent: Automating Quadratic Unconstrained Binary Optimization (QUBO) Formulation Generation from Natural Language
Niloy Kumar Mondal, Md Rizwan Parvez
Quadratic Unconstrained Binary Optimization (QUBO) is a central formulation for combinatorial optimization and has gained increasing attention due to its compatibility with quantum…
GUI-Primitives: Diagnosing Spatial Reasoning Failures in Vision-Language GUI Grounding
Md Abrar Jahin, Md Rizwan Parvez
Computer-use agents ground natural-language instructions in screenshots to locate interface elements, yet existing benchmarks do not isolate whether models bind relational language…
Poison with Style: A Practical Poisoning Attack on Code Large Language Models
Khang Tran, Yazan Boshmaf, Issa Khalil +3
Code Large Language Models (CLLMs) serve as the core of modern code agents, enabling developers to automate complex software development tasks. In this paper, we present Poison-wit…
Self-Consistency from Only Two Samples: CoT-PoT Ensembling for Efficient LLM Reasoning
Raman Saparkhan, Majd Hawasly, Md Rizwan Parvez +1
Self-consistency (SC) is a popular technique for improving the reasoning accuracy of large language models by aggregating multiple sampled outputs, but it comes at a high computati…
Omni-Modal Dissonance Benchmark: Systematically Breaking Modality Consensus to Probe Robustness and Calibrated Abstention
Zabir Al Nazi, Shubhashis Roy Dipta, Md Rizwan Parvez
Existing omni-modal benchmarks attempt to measure modality-specific contributions, but their measurements are confounded: naturally co-occurring modalities carry correlated yet une…
TimeSpot: Benchmarking Geo-Temporal Understanding in Vision-Language Models in Real-World Settings
Azmine Toushik Wasi, Shahriyar Zaman Ridoy, Koushik Ahamed Tonmoy +5
Geo-temporal understanding, the ability to infer location, time, and contextual properties from visual input alone, underpins applications such as disaster management, traffic plan…
SpatiaLab: Can Vision-Language Models Perform Spatial Reasoning in the Wild?
Azmine Toushik Wasi, Wahid Faisal, Abdur Rahman +12
Spatial reasoning is a fundamental aspect of human cognition, yet it remains a major challenge for contemporary vision-language models (VLMs). Prior work largely relied on syntheti…
Reward Engineering for Software Tasks: A Survey of Reinforcement Learning Approaches
Md Rayhanul Masud, Azmine Toushik Wasi, Salman Rahman +1
Reinforcement learning is increasingly used for code-centric software engineering tasks, including code generation, understanding, repair, testing, and optimization, especially wit…