🔥Telegram İfşa

Had a great time presenting our papers at NAACL 2025! Appreciate all the engaging conversations and connections. #NAACL2025 #AIresearch #LLMs #ResponsibleAI

Read our paper : aclanthology.org/2025.knowledge…

📢 Calling all SEA-passionate individuals! SEACrowd is excited to launch our contributor call for SEA-VL Phase 2: Building Visual Language Models for Southeast Asia! 🌏 After the success of Phase 1 where we created a culturally grounded image dataset and benchmarking study we're

🚀 Excited to introduce EasyEdit2 — a powerful upgrade to EasyEdit, now redesigned for unified, plug-and-play LLM behavior steering at inference time! #EasyEdit #LLM #ModelSteering #ModelEditing #KnowledgeEditing #EasyEdit2 #AI #InferenceTimeControl ✨ No retraining — just

🌏 Join SEA-VL Phase 2 – Help Build a Vision-Language Model for Southeast Asia! We’re thrilled to announce the launch of SEA-VL Phase 2, a global community initiative to build VLMs that truly understands SEA—its languages, cultures, and visual richness.🧵(1/x) #nlproc #seacrowd

Phase 2 open contribution call! Please join join 🤗

4/6 papers accepted to #ACL2025. Vienna, here I come! Huge thanks to my amazing co-authors. Can’t wait to share what we’ve been working on! 🎉🎉✈️

Big news! Three of our papers have been accepted to ACL 2025 in Vienna! Grateful to all collaborators and reviewers. Excited to present our work and learn from the global NLP community. See you in Austria this August! #ACL2025 #NLP #AI

SEA-VL has been accepted at ACL 2025! Congratulations to all involved! Phase 2 is also ongoing: x.com/seacrowd_ai/st… #multimodal #multiculture

This has been accepted to ACL2025 (Main) 🥳 Happy to have contributed so much to this project, along with my amazing collaborators at SEACrowd !

We have finally made the dataset public for everyone to use: [link in the comments] SweEval got accepted in NAACL '25 industry track. It already has 120+ downloads, try out our dataset to know how LLMs fare with swear words! #nlpoli #research #acl2025 #naacl #LLMs #claude #gpt

Hard Negative Mining for Domain-Specific Retrieval in Enterprise Systems Oracle presents a scalable hard-negative mining framework for domain-specific enterprise data, dynamically selecting challenging negatives to enhance re-ranking models. 📝arxiv.org/abs/2505.18366

Based on simple yet effective semantic selection criterion: 1. Negatives closer to the query than positives; 2. Yet far enough from the positive to avoid noise; Use clustering and dimensionality reduction to do negative sampling at scale.

Explore this cross-lingual safety evaluation & contribute! Dataset: huggingface.co/datasets/arion… Details: huggingface.co/papers/2505.17…

Excited to announce arion das || gen-ai research || nlp || llms, CS undergrad at IIIT Ranchi and co-author of "SweEval: Do LLMs Really Swear?", will be speaking at our AI safety and alignment group. He'll discuss LLM safety, handling sensitive language, and insights from the SweEval-Bench dataset.

🚀 Excited to share that four of our papers have been accepted to #ACL2025! Grateful to see our work across multimodal learning, retrieval, and speech recognized this year. While I won’t be attending in person, our team will be there to present and connect on-site. Accepted

Sad to miss ACL in Vienna but so many of our members of SEACrowd are going to be there to present this work🔥 Reach out or find us in our merch 😉 Learn about our ongoing cool initiatives and how to participate or get our merch 😎

Our new work on test-time adaptation has been accepted at #CIKM2025 (ACM CIKM 2025)! I would like to thank my Ph.D. advisor, Prof. Chae and collaborators Amit and Hitesh Laxmichand Patel for their contributions!

Excited to host Hitesh Laxmichand Patel for an engaging talk on the responsible use of AI, NLP and navigating grad school applications. #nlp #iiitranchi #research #agentic_ai #generativeai #GPT5