Related papers: Qwen2.5-32B: Leveraging Self-Consistent Tool-Integ…

With reasoning language models such as OpenAI-o3 and DeepSeek-R1 emerging, large language models (LLMs) have entered a new phase of development. However, existing benchmarks for coding evaluation are gradually inadequate to assess the…

In this report, we introduce the Qwen2.5-Coder series, a significant upgrade from its predecessor, CodeQwen1.5. This series includes six models: Qwen2.5-Coder-(0.5B/1.5B/3B/7B/14B/32B). As a code-specific model, Qwen2.5-Coder is built upon…

Long-form chain-of-thought reasoning has become a cornerstone of advanced reasoning in large language models. While recent verification-refinement frameworks have enabled proprietary models to solve Olympiad-level problems, their…

Tool-Integrated Reasoning (TIR) extends LLM capabilities by leveraging external environments. However, existing methods lack the deliberation during sequential tool invocation required for strategic planning and self-correction. While RL…

Large reasoning models (LRMs) like OpenAI-o1 have shown impressive capabilities in natural language reasoning. However, these models frequently demonstrate inefficiencies or inaccuracies when tackling complex mathematical operations. While…

Bengali is a prominent language of the Indian subcontinent. However, while many state-of-the-art acoustic models exist for prominent languages spoken in the region, research and resources for Bengali are few and far between. In this work,…

Despite the growing progress in Natural Language Inference (NLI) research, resources for the Bengali language remain extremely limited. Existing Bengali NLI datasets exhibit several inconsistencies, including annotation errors, ambiguous…

Language models have demonstrated remarkable performance on complex multi-step reasoning tasks. However, their evaluation has been predominantly confined to high-resource languages such as English. In this paper, we introduce a manually…

An AI chatbot provides an impressive response after learning from the trained dataset. In this decade, most of the research work demonstrates that deep neural models superior to any other model. RNN model regularly used for determining the…

We propose a novel three-step prompt-tuning method for Bengali Grammatical Error Explanation (BGEE) using state-of-the-art large language models (LLMs) such as GPT-4, GPT-3.5 Turbo, and Llama-2-70b. Our approach involves identifying and…

We present BlueLM-2.5-3B, a compact and unified dense Multimodal Large Language Model (MLLM) designed for efficient edge-device deployment, offering strong general-purpose and reasoning capabilities. To the best of our knowledge, this is…

Large language models (LLMs) have recently achieved significant advances in reasoning and demonstrated their advantages in solving challenging problems. Yet, their effectiveness in the semiconductor display industry remains limited due to a…

The rapid development of digital stages has greatly compounded the dispersal of untrue data, dissolving certainty and judgment in society, especially among the Bengali-speaking community. Our ponder addresses this critical issue by…

The Qwen 2.5 3B base model was fine-tuned to generate contextually rich and engaging movie dialogue, leveraging the Cornell Movie-Dialog Corpus, a curated dataset of movie conversations. Due to the limitations in GPU computing and VRAM, the…

Automatic detection and recognition of banknotes can be a very useful technology for people with visual difficulties and also for the banks itself by providing efficient management for handling different paper currencies. Lightweight models…

Bengali, despite being one of the most widely spoken languages globally, remains underrepresented in long form speech technology, particularly in systems addressing transcription and speaker attribution. We present frameworks for long form…

As Large Language Models (LLMs) are rapidly evolving, providing accurate feedback and scalable oversight on their outputs becomes an urgent and critical problem. Leveraging LLMs as critique models to achieve automated supervision is a…

Racism is an alarming phenomenon in our country as well as all over the world. Every day we have come across some racist comments in our daily life and virtual life. Though we can eradicate this racism from virtual life (such as Social…

Mathematical Word Problems (MWPs) are among the most challenging tasks in natural language processing because they require both linguistic understanding and multi-step numerical reasoning. While Chain-of-Thought (CoT) prompting has shown…

Ensembling neural machine translation (NMT) models to produce higher-quality translations than the $L$ individual models has been extensively studied. Recent methods typically employ a candidate selection block (CSB) and an encoder-decoder…