ข่าว
Start Making Sense(s): A Developmental Probe of Attention Specialization Using Lexical Ambiguity
arXiv:2511.21974v1 Announce Type: new Abstract: Despite an in-principle understanding of self-attention matrix operations in Transformer...
STAR-Bench: Probing Deep Spatio-Temporal Reasoning as Audio 4D Intelligence
arXiv:2510.24693v2 Announce Type: replace-cross Abstract: Despite rapid progress in Multi-modal Large Language Models and Large...
Stand Up for Research, Innovation, and Education
Right now, MIT alumni and friends are voicing their support for: America’s scientific and technological...
Stacked from One: Multi-Scale Self-Injection for Context Window Extension
arXiv:2603.04759v1 Announce Type: new Abstract: The limited context window of contemporary large language models (LLMs)...
Stable Signer: Hierarchical Sign Language Generative Model
arXiv:2512.04048v1 Announce Type: cross Abstract: Sign Language Production (SLP) is the process of converting the...
SRA-MCTS: Self-driven Reasoning Augmentation with Monte Carlo Tree Search for Code Generation
arXiv:2411.11053v5 Announce Type: replace Abstract: Large language models demonstrate exceptional performance in simple code generation...
SR-GRPO: Stable Rank as an Intrinsic Geometric Reward for Large Language Model Alignment
arXiv:2512.02807v1 Announce Type: new Abstract: Aligning Large Language Models (LLMs) with human preferences typically relies...
SQLong: Enhanced NL2SQL for Longer Contexts with LLMs
arXiv:2502.16747v2 Announce Type: replace Abstract: Open-weight large language models (LLMs) have significantly advanced performance in...
Spott’s AI-native recruiting platform scores $3.2M to end hiring software chaos
Spott secures $3.2 million in funding to build an all-in-one AI-native recruitment platform that automates...
SPG: Sandwiched Policy Gradient for Masked Diffusion Language Models
arXiv:2510.09541v1 Announce Type: new Abstract: Diffusion large language models (dLLMs) are emerging as an efficient...
SpeechMedAssist: Efficiently and Effectively Adapting Speech Language Models for Medical Consultation
arXiv:2601.04638v1 Announce Type: new Abstract: Medical consultations are intrinsically speech-centric. However, most prior works focus...
SpecEdge: Scalable Edge-Assisted Serving Framework for Interactive LLMs
arXiv:2505.17052v2 Announce Type: replace Abstract: Large language models (LLMs) power many modern applications, but serving...
