News
Skip Connections in Transformer Models
This post is divided into three parts; they are: • Why Skip Connections are Needed...
Single Word Change is All You Need: Using LLMs to Create Synthetic Training Examples for Text Classifiers
arXiv:2401.17196v3 Announce Type: replace Abstract: In text classification, creating an adversarial example means subtly perturbing...
SINAI at eRisk@CLEF 2025: Transformer-Based and Conversational Strategies for Depression Detection
arXiv:2509.19861v1 Announce Type: new Abstract: This paper describes the participation of the SINAI-UJA team in...
SimpleDeepSearcher: Deep Information Seeking via Web-Powered Reasoning Trajectory Synthesis
arXiv:2505.16834v3 Announce Type: replace Abstract: Retrieval-augmented generation (RAG) systems have advanced large language models (LLMs)...
Shrink exploit windows, slash MTTP: Why ring deployment is now a must for enterprise defense
Ring deployment slashes MTTP and legacy CVE risk. Learn how Ivanti and Southstar Bank are...
SGPO: Self-Generated Preference Optimization based on Self-Improver
arXiv:2507.20181v1 Announce Type: new Abstract: Large language models (LLMs), despite their extensive pretraining on diverse...
SessionIntentBench: A Multi-task Inter-session Intention-shift Modeling Benchmark for E-commerce Customer Behavior Understanding
arXiv:2507.20185v1 Announce Type: new Abstract: Session history is a common way of recording user interacting...
ServiceNow AI Releases Apriel-1.5-15B-Thinker: An Open-Weights Multimodal Reasoning Model that Hits Frontier-Level Performance on a Single-GPU Budget
ServiceNow AI Research Lab has released Apriel-1.5-15B-Thinker, a 15-billion-parameter open-weights multimodal reasoning model trained with...
ServiceNow AI Released Apriel-Nemotron-15b-Thinker: A Compact Yet Powerful Reasoning Model Optimized for Enterprise-Scale Deployment and Efficiency
AI models today are expected to handle complex tasks such as solving mathematical problems, interpreting...
Sequence graphs realizations and ambiguity in language models
arXiv:2402.08830v2 Announce Type: replace-cross Abstract: Several popular language models represent local contexts in an input...
Sentiment-Aware Recommendation Systems in E-Commerce: A Review from a Natural Language Processing Perspective
arXiv:2505.03828v1 Announce Type: cross Abstract: E-commerce platforms generate vast volumes of user feedback, such as...
Sentient AI Releases ROMA: An Open-Source and AGI Focused Meta-Agent Framework for Building AI Agents with Hierarchical Task Execution
Sentient AI has released ROMA (Recursive Open Meta-Agent), an open-source meta-agent framework for building high-performance...
