BanglaTalk: Towards Real-Time Speech Assistance for Bengali Regional Dialects Paper • 2510.06188 • Published Oct 7, 2025
Read Between the Lines: A Benchmark for Uncovering Political Bias in Bangla News Articles Paper • 2510.03898 • Published Oct 4, 2025
BanglaIPA: Towards Robust Text-to-IPA Transcription with Contextual Rewriting in Bengali Paper • 2601.01778 • Published Jan 5
†DAGGER: Distractor-Aware Graph Generation for Executable Reasoning in Math Problems Paper • 2601.06853 • Published Jan 11
GanitLLM: Difficulty-Aware Bengali Mathematical Reasoning through Curriculum-GRPO Paper • 2601.06767 • Published Jan 11 • 1
Learning How to Use Tools, Not Just When: Pattern-Aware Tool-Integrated Reasoning Paper • 2509.23292 • Published Sep 27, 2025
UAT-LITE: Inference-Time Uncertainty-Aware Attention for Pretrained Transformers Paper • 2602.02952 • Published Feb 3
Advancing Reference-free Evaluation of Video Captions with Factual Analysis Paper • 2509.16538 • Published Sep 20, 2025 • 2
FedMentor: Domain-Aware Differential Privacy for Heterogeneous Federated LLMs in Mental Health Paper • 2509.14275 • Published Sep 16, 2025
Can LLMs Obfuscate Code? A Systematic Analysis of Large Language Models into Assembly Code Obfuscation Paper • 2412.16135 • Published Dec 20, 2024
Do LLMs Adhere to Label Definitions? Examining Their Receptivity to External Label Definitions Paper • 2509.02452 • Published Sep 2, 2025
WellDunn: On the Robustness and Explainability of Language Models and Large Language Models in Identifying Wellness Dimensions Paper • 2406.12058 • Published Jun 17, 2024
LingVarBench: Benchmarking LLM for Automated Named Entity Recognition in Structured Synthetic Spoken Transcriptions Paper • 2508.15801 • Published Aug 13, 2025
Q2E: Query-to-Event Decomposition for Zero-Shot Multilingual Text-to-Video Retrieval Paper • 2506.10202 • Published Jun 11, 2025
If We May De-Presuppose: Robustly Verifying Claims through Presupposition-Free Question Decomposition Paper • 2508.16838 • Published Aug 22, 2025 • 1