CHANNEL ARCHIVE // [345] ARTICLES // PAGE 16 OF 23
Artificial Intelligence
Research into artificial intelligence and intelligent systems.
CHANNEL // 01 [345]
Artificial Intelligence
Research into artificial intelligence and intelligent systems.
LoRA-Patch steers model activations to weaken backdoored adapters
Source published
- LoRA adapters
- language model security
- backdoor mitigation
CAST-Bench tests whether AI-generated sounds belong to the right scene and speaker
Source published
- CAST-Bench
- audio-video generation
- multimodal evaluation
A Stock-News RAG Prototype Reports Fast Answers, but Accuracy Remains an Open Question
Source published
- retrieval-augmented generation
- financial information retrieval
- Vietnamese stock-market news
EvoMemState gives AI memories context—and rules for using it
Source published
- EvoMemState
- AI agent memory
- personal agents
Could the shape of word connections help evaluate AI reasoning?
Source published
- AI reasoning
- topological data analysis
- co-occurrence persistent homology
Could sleep-inspired maintenance help AI agents manage their memories?
Source published
- AI agents
- persistent memory
- memory consolidation
HyVox pairs two kinds of chips to cut the energy cost of speaker identification
Source published
- HyVox
- speaker identification
- neuromorphic computing
Learning to reconstruct single-pixel video from noisy-looking feedback
Source published
- single-pixel imaging
- video reconstruction
- residual images
DualClusterNet combines shared mobility patterns with personal context to predict the next place
Source published
- DualClusterNet
- next-POI recommendation
- mobility prediction
RAGLog looks for hidden faults behind AI-generated answers
Source published
- retrieval-augmented generation
- RAGLog
- fault localization
EMBERS probes how AI research agents fail when questions and searches change
Source published
- EMBERS
- Deep Research
- AI research agents
AI-guided plasma simulations separate stronger heating from brighter X-rays
Source published
- Simjecture
- AI-assisted research
- computational physics
Nepali speech benchmark reveals gaps between automated scores and native listeners
Source published
- Nepali text-to-speech
- NepTTS-Bench
- NepaliMOS
PhysFTM reconstructs physical fields from sparse sensors and missing frames
Source published
- PhysFTM
- sparse sensors
- spatiotemporal reconstruction
A Zero-Starting Gate for Adding Non-Text Inputs to Frozen Language Models
Source published
- cross-attention
- frozen language models
- multimodal adaptation