All Articles
arXiv:2602.21619v1 Announce Type: new Abstract: Visual spatial reasoning (VSR) remains challenging for modern vision-language models (VLMs), despite advances in multimodal architectures. A common strategy is …
arXiv:2602.21628v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a prevailing paradigm for enhancing reasoning in Multimodal Large Language Models …
arXiv:2602.21638v1 Announce Type: new Abstract: Effectively addressing client resistance is a sophisticated clinical skill in psychological counseling, yet practitioners often lack timely and scalable supervisory …
arXiv:2602.21646v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have achieved notable success in enhancing translation performance by integrating multimodal information. However, existing research …
arXiv:2602.21647v1 Announce Type: new Abstract: This paper presents and evaluates an optimized cascaded Nepali speech-to-English text translation (S2TT) system, focusing on mitigating structural noise introduced …
arXiv:2602.21652v1 Announce Type: new Abstract: Large language models have demonstrated capabilities in text generation, while their increasing parameter scales present challenges in computational and memory …
arXiv:2602.21669v1 Announce Type: new Abstract: Knowledge Distillation (KD) has emerged as a crucial technique for compressing Large Language Models (LLMs). Although existing cross-tokenizer KD methods …
arXiv:2602.21720v1 Announce Type: new Abstract: Human recursive numeral systems (i.e., counting systems such as English base-10 numerals), like many other grammatical systems, are highly regular. …
arXiv:2602.21728v1 Announce Type: new Abstract: The reasoning process of Large Language Models (LLMs) is often plagued by hallucinations and missing facts in question-answering tasks. A …
arXiv:2602.21741v1 Announce Type: new Abstract: We describe our end-to-end system for Bengali long-form speech recognition (ASR) and speaker diarization submitted to the DL Sprint 4.0 …
arXiv:2602.21763v1 Announce Type: new Abstract: Implicit Discourse Relation Recognition (IDRR) remains a challenging task due to the requirement for deep semantic understanding in the absence …
arXiv:2602.21786v1 Announce Type: new Abstract: Chain-of-Thought (CoT) distillation from Large Language Models (LLMs) often induces "overthinking" in Small Language Models (SLMs), leading to performance degradation …
