Zobrazeno 1 - 10
of 1 386
pro vyhledávání: '"Soujanya, P"'
In recent years, several proposals that leverage principles from condensed matter and high-energy physics for engineering laser arrays have been put forward. The most important among these concepts are topology, which enables the construction of robu
Externí odkaz:
http://arxiv.org/abs/2412.12275
Autor:
Sun, Qi, Hong, Pengfei, Pala, Tej Deep, Toh, Vernon, Tan, U-Xuan, Ghosal, Deepanway, Poria, Soujanya
Traditional reinforcement learning-based robotic control methods are often task-specific and fail to generalize across diverse environments or unseen objects and instructions. Visual Language Models (VLMs) demonstrate strong scene understanding and p
Externí odkaz:
http://arxiv.org/abs/2412.11974
Autor:
Chia, Yew Ken, Cheng, Liying, Chan, Hou Pong, Liu, Chaoqun, Song, Maojia, Aljunied, Sharifah Mahani, Poria, Soujanya, Bing, Lidong
The ability to understand and answer questions over documents can be useful in many business and practical applications. However, documents often contain lengthy and diverse multimodal contents such as texts, figures, and tables, which are very time-
Externí odkaz:
http://arxiv.org/abs/2411.06176
The limited context window of contemporary large language models (LLMs) remains a huge barrier to their broader application across various domains. While continual pre-training on long-context data is a straightforward and effective solution, it incu
Externí odkaz:
http://arxiv.org/abs/2410.19318
Large language models (LLMs) have shown increasing competence in solving mathematical reasoning problems. However, many open-source LLMs still struggle with errors in calculation and semantic understanding during intermediate reasoning steps. In this
Externí odkaz:
http://arxiv.org/abs/2410.12608
Autor:
Mihalcea, Rada, Ignat, Oana, Bai, Longju, Borah, Angana, Chiruzzo, Luis, Jin, Zhijing, Kwizera, Claude, Nwatu, Joan, Poria, Soujanya, Solorio, Thamar
This paper presents a vision for creating AI systems that are inclusive at every stage of development, from data collection to model design and evaluation. We address key limitations in the current AI pipeline and its WEIRD representation, such as la
Externí odkaz:
http://arxiv.org/abs/2410.16315
Autor:
Yang, Zonglin, Liu, Wanhao, Gao, Ben, Xie, Tong, Li, Yuqiang, Ouyang, Wanli, Poria, Soujanya, Cambria, Erik, Zhou, Dongzhan
Scientific discovery contributes largely to human society's prosperity, and recent progress shows that LLMs could potentially catalyze this process. However, it is still unclear whether LLMs can discover novel and valid hypotheses in chemistry. In th
Externí odkaz:
http://arxiv.org/abs/2410.07076
Advanced models such as OpenAI o1 exhibit impressive problem-solving capabilities through step-by-step reasoning. However, they may still falter on more complex problems, making errors that disrupt their reasoning paths. We attribute this to the expa
Externí odkaz:
http://arxiv.org/abs/2410.10858
Large multimodal models have demonstrated impressive problem-solving abilities in vision and language tasks, and have the potential to encode extensive world knowledge. However, it remains an open challenge for these models to perceive, reason, plan,
Externí odkaz:
http://arxiv.org/abs/2409.14277
Autor:
Song, Maojia, Sim, Shang Hong, Bhardwaj, Rishabh, Chieu, Hai Leong, Majumder, Navonil, Poria, Soujanya
LLMs are an integral component of retrieval-augmented generation (RAG) systems. While many studies focus on evaluating the overall quality of end-to-end RAG systems, there is a gap in understanding the appropriateness of LLMs for the RAG task. To add
Externí odkaz:
http://arxiv.org/abs/2409.11242