6 citations · 16 across the 15 of their papers we have counts for
16 papers
SCOReD: Student-Aware CoT Optimization for Recommendation Distillation
Haz Sameen Shahgir, Yufei Li, Xiaohan Wei +8
Chain-of-thought (CoT) distillation in the recommendation domain is a necessary precursor to RL training, but raw teacher traces are ill-suited to this task. Large teachers approac…
D-Judge: Disrupting Multi-Turn Jailbreaks using Semantics-Preserving Output Rewriting
Huanli Gong, Zhipeng Wei, Yu Fu +4
Multi-turn jailbreak attacks pose a growing threat to large language model (LLM) safety because they exploit feedback from auxiliary judge models to iteratively refine prompts towa…
Reducing the Safety Tax in LLM Safety Alignment with On-Policy Self-Distillation
Yu Fu, Longxuan Yu, Haz Sameen Shahgir +4
Safety alignment often improves robustness to harmful queries at the cost of reasoning ability, a tradeoff known as the safety tax. A common cause is distributional mismatch: super…
VLMs Need Words: Vision Language Models Ignore Visual Detail In Favor of Semantic Anchors
Haz Sameen Shahgir, Xiaofu Chen, Yu Fu +4
Vision-language models (VLMs) have achieved impressive performance across a wide range of multimodal tasks. However, they often fail on tasks that require fine-grained visual perce…
Do Reasoning LLMs Refuse What They Infer in Long Contexts?
Yu Fu, Haz Sameen Shahgir, Huanli Gong +3
Long-context LLMs can infer objectives that are not stated explicitly. This capability is useful for reasoning over documents, code, retrieved evidence, and tool traces, but it als…
A Real-Time System to Populate FRA Form 57 from News
Chansong Lim, Haz Sameen Shahgir, Yue Dong +2
Local railway committees need timely situational awareness after highway-rail grade crossing incidents, yet official Federal Railroad Administration (FRA) investigations can take d…
AbFlowNet: Optimizing Antibody-Antigen Binding Energy via Diffusion-GFlowNet Fusion
Abrar Rahman Abir, Haz Sameen Shahgir, Md Rownok Zahan Ratul +3
Complementarity Determining Regions (CDRs) are critical segments of an antibody that facilitate binding to specific antigens. Current computational methods for CDR design utilize r…
LELANTE: LEveraging LLM for Automated ANdroid TEsting
Shamit Fatin, Mehbubul Hasan Al-Quvi, Haz Sameen Shahgir +6
Given natural language test case description for an Android application, existing testing approaches require developers to manually write scripts using tools such as Appium and Esp…
Harnessing the Unseen: The Hidden Influence of Intrinsic Knowledge in Long-Context Language Models
Yu Fu, Haz Sameen Shahgir, Hui Liu +3
Recent advances in long-context language models (LCLMs), designed to handle extremely long contexts, primarily focus on utilizing external contextual information, often leaving the…
ExpertGenQA: Open-ended QA generation in Specialized Domains
Haz Sameen Shahgir, Chansong Lim, Jia Chen +2
Generating high-quality question-answer pairs for specialized technical domains remains challenging, with existing approaches facing a tradeoff between leveraging expert examples a…
Too Late to Train, Too Early To Use? A Study on Necessity and Viability of Low-Resource Bengali LLMs
Tamzeed Mahfuz, Satak Kumar Dey, Ruwad Naswan +3
Each new generation of English-oriented Large Language Models (LLMs) exhibits enhanced cross-lingual transfer capabilities and significantly outperforms older LLMs on low-resource…
IllusionVQA: A Challenging Optical Illusion Dataset for Vision Language Models
Haz Sameen Shahgir, Khondker Salman Sayeed, Abhik Bhattacharjee +3
The advent of Vision Language Models (VLM) has allowed researchers to investigate the visual understanding of a neural network using natural language. Beyond object classification…
Asymmetric Bias in Text-to-Image Generation with Adversarial Attacks
Haz Sameen Shahgir, Xianghao Kong, Greg Ver Steeg +1
The widespread use of Text-to-Image (T2I) models in content generation requires careful examination of their safety, including their robustness to adversarial attacks. Despite exte…
Leveraging Complementary Attention maps in vision transformers for OCT image analysis
Haz Sameen Shahgir, Tanjeem Azwad Zaman, Khondker Salman Sayeed +3
Optical Coherence Tomography (OCT) scan yields all possible cross-section images of a retina for detecting biomarkers linked to optical defects. Due to the high volume of data gene…
BanglaCoNER: Towards Robust Bangla Complex Named Entity Recognition
HAZ Sameen Shahgir, Ramisa Alam, Md. Zarif Ul Alam
Named Entity Recognition (NER) is a fundamental task in natural language processing that involves identifying and classifying named entities in text. But much work hasn't been done…
Applying wav2vec2 for Speech Recognition on Bengali Common Voices Dataset
H. A. Z. Sameen Shahgir, Khondker Salman Sayeed, Tanjeem Azwad Zaman
Speech is inherently continuous, where discrete words, phonemes and other units are not clearly segmented, and so speech recognition has been an active research problem for decades…