Recent Research Signals

Found 496 results

Filtering papers...

Paper	Possible Impact	Features	Possible Business Area
hls4ml: A Flexible, Open-Source Platform for Deep Learning Acceleration on Reconfigurable Hardware Hardware Architecture	Makes smart computer programs run super fast.	Massachusetts Institute of Technology Siemens University of Washington Code 5 Countries	Field-Programmable Gate Array (FPGA) (79%)	Score: 5 4 days ago
CycliST: A Video Language Model Benchmark for Reasoning on Cyclical State Transitions CV and Pattern Recognition	Teaches computers to understand repeating patterns in videos.	Code Data 2 Countries	Image Recognition (77%)	Score: 4 5 days ago
Privacy-Preserving Generative Modeling and Clinical Validation of Longitudinal Health Records for Chronic Disease Machine Learning (CS)	Creates fake patient data to train medical AI.	Stanford University Code 2 Countries	Predictive Analytics (78%)	Score: 4 6 days ago
The Trojan Knowledge: Bypassing Commercial LLM Guardrails via Harmless Prompt Weaving and Adaptive Tree Search Cryptography and Security	Breaks AI safety by tricking it with hidden questions.	IBM Code 2 Countries	Natural Language Processing (76%)	Score: 4 4 days ago
Distill, Forget, Repeat: A Framework for Continual Unlearning in Text-to-Image Diffusion Models Machine Learning (CS)	Removes unwanted data from AI without retraining.	Sony PlayStation Code 2 Countries	Machine Learning (77%)	Score: 4 3 days ago
MoReGen: Multi-Agent Motion-Reasoning Engine for Code-based Text-to-Video Synthesis CV and Pattern Recognition	Makes videos follow real-world physics rules.	Microsoft Code 2 Countries	Motion Capture (80%)	Score: 4 2 days ago
A Wolf in Sheep's Clothing: Bypassing Commercial LLM Guardrails via Harmless Prompt Weaving and Adaptive Tree Search Cryptography and Security	Breaks AI safety rules by tricking its knowledge.	Code 2 Countries	Natural Language Processing (76%)	Score: 3 4 days ago
Towards Irreversible Machine Unlearning for Diffusion Models Machine Learning (CS)	Makes AI forget unwanted pictures, safely.	Code 2 Countries	Machine Learning (76%)	Score: 3 2 days ago
Rectifying LLM Thought from Lens of Optimization Computation and Language	Teaches computers to think smarter, not longer.	Code Data	Natural Language Processing (78%)	Score: 3 4 days ago
Equivariant Symmetry-Aware Head Pose Estimation for Fetal MRI CV and Pattern Recognition	Helps doctors see babies better during scans.	Massachusetts Institute of Technology Code	Image Recognition (75%)	Score: 3 1 day ago
UniCom: Towards a Unified and Cohesiveness-aware Framework for Community Search and Detection Social and Information Networks	Finds groups in networks without needing new training.	Code 2 Countries	Semantic Search (79%)	Score: 3 3 days ago
Four Over Six: More Accurate NVFP4 Quantization with Adaptive Block Scaling Computation and Language	Makes AI models train faster and better.	Massachusetts Institute of Technology Code	Quantum Computing (73%)	Score: 3 4 days ago
CAR-Net: A Cascade Refinement Network for Rotational Motion Deblurring under Angle Information Uncertainty CV and Pattern Recognition	Fixes blurry pictures from spinning.	Code 2 Countries	Image Recognition (76%)	Score: 3 6 days ago
PhyDetEx: Detecting and Explaining the Physical Plausibility of T2V Models CV and Pattern Recognition	Teaches AI to spot videos breaking physics rules.	Code 2 Countries	Image Recognition (77%)	Score: 3 4 days ago
Generative AI for Self-Adaptive Systems: State of the Art and Research Roadmap Software Engineering	Makes smart systems learn and adapt better.	Code 3 Countries	Intelligent Systems (83%)	Score: 3 1 day ago
BlurDM: A Blur Diffusion Model for Image Deblurring CV and Pattern Recognition	Fixes blurry pictures by reversing how they got blurry.	NVIDIA Code 2 Countries	Simulation (73%)	Score: 3 2 days ago
TRoVe: Discovering Error-Inducing Static Feature Biases in Temporal Vision-Language Models CV and Pattern Recognition	Finds hidden mistakes in AI that watches videos.	Stanford University Code	Image Recognition (77%)	Score: 3 5 days ago
Artographer: a Curatorial Interface for Art Space Exploration Human-Computer Interaction	Helps you find art connections on a visual map.	University of California, Berkeley University of Washington Code	Human Computer Interaction (80%)	Score: 3 4 days ago
CoDA: From Text-to-Image Diffusion Models to Training-Free Dataset Distillation CV and Pattern Recognition	Makes AI learn from less data, faster.	Code 2 Countries	Image Recognition (76%)	Score: 3 2 days ago
UserSimCRS v2: Simulation-Based Evaluation for Conversational Recommender Systems Information Retrieval	Builds better chatbots that suggest things you like.	Code 2 Countries	Simulation (80%)	Score: 3 1 day ago
Lumos: Let there be Language Model System Certification Programming Languages	Finds dangerous mistakes in AI that drives cars.	Code 2 Countries	Natural Language Processing (77%)	Score: 3 3 days ago
LLM-as-a-Judge for Scalable Test Coverage Evaluation: Accuracy, Operational Reliability, and Cost Software Engineering	Tests computer programs faster and cheaper.	MasterCard Code 2 Countries	Natural Language Processing (77%)	Score: 3 5 days ago
LLM CHESS: Benchmarking Reasoning and Instruction-Following in LLMs through Chess Artificial Intelligence	Tests how well AI plays and understands chess.	University of California, Berkeley Code	Machine Learning (78%)	Score: 3 4 days ago
Label Forensics: Interpreting Hard Labels in Black-Box Text Classifier Machine Learning (CS)	Uncovers what hidden computer text labels mean.	Code Data 2 Countries	Text Analytics (79%)	Score: 3 4 days ago
Spatiotemporal Pyramid Flow Matching for Climate Emulation CV and Pattern Recognition	Models climate change faster and more accurately.	Stanford University Code	Simulation (77%)	Score: 3 4 days ago
Silhouette-based Gait Foundation Model CV and Pattern Recognition	Lets computers recognize people by how they walk.	Johns Hopkins University Code 2 Countries	Image Recognition (77%)	Score: 3 6 days ago
Four Over Six: More Accurate NVFP4 Quantization with Adaptive Block Scaling Computation and Language	Trains AI faster and better using less computer memory.	Massachusetts Institute of Technology Code	A/B Testing (73%)	Score: 3 4 days ago
ProteinPNet: Prototypical Part Networks for Concept Learning in Spatial Proteomics Machine Learning (CS)	Finds hidden patterns in cancer cells.	University of California, Berkeley Code 2 Countries	Bioinformatics (76%)	Score: 3 3 days ago
G-KV: Decoding-Time KV Cache Eviction with Global Attention Computation and Language	Makes AI remember more without slowing down.	Microsoft Code 2 Countries	Natural Language Processing (75%)	Score: 3 6 days ago
AdaptVision: Efficient Vision-Language Models via Adaptive Visual Acquisition CV and Pattern Recognition	Lets computers see smarter, using less data.	Code Data	Image Recognition (80%)	Score: 3 2 days ago
Panda: Self-distillation of Reusable Sensor-level Representations for High Energy Physics High Energy Physics - Experiment	Teaches computers to see tiny particle paths.	Code	Image Recognition (77%)	Score: 2 4 days ago
LAP: Fast LAtent Diffusion Planner with Fine-Grained Feature Distillation for Autonomous Driving Robotics	Makes self-driving cars plan faster and smarter.	Code	Autonomous Vehicles (79%)	Score: 2 6 days ago
Realistic Handwritten Multi-Digit Writer (MDW) Number Recognition Challenges CV and Pattern Recognition	Helps computers read whole numbers, not just single digits.	Code Data	Image Recognition (79%)	Score: 2 6 days ago
SCALE: Selective Resource Allocation for Overcoming Performance Bottlenecks in Mathematical Test-time Scaling Computation and Language	Smartly gives computers more thinking power for hard math.	Code Data	Quantum Computing (77%)	Score: 2 6 days ago
EDIT: Early Diffusion Inference Termination for dLLMs Based on Dynamics of Training Gradients Artificial Intelligence	Makes AI think faster and use less energy.	Intel Code	Natural Language Processing (76%)	Score: 2 6 days ago
ZO-ASR: Zeroth-Order Fine-Tuning of Speech Foundation Models without Back-Propagation Multimedia	Makes speech recognition work with less computer power.	Code	Speech Recognition (76%)	Score: 2 4 days ago
Accelerating Large-Scale Reasoning Model Inference with Sparse Self-Speculative Decoding Machine Learning (CS)	Makes AI answer questions much faster.	Code	Semantic Search (75%)	Score: 2 4 days ago
CuES: A Curiosity-driven and Environment-grounded Synthesis Framework for Agentic RL Artificial Intelligence	Teaches AI to invent its own learning games.	Alibaba Code	Artificial Intelligence (77%)	Score: 2 4 days ago
Fourier Neural Operators Explained: A Practical Perspective Machine Learning (CS)	Teaches computers to solve hard math problems faster.	Code	Natural Language Processing (76%)	Score: 2 4 days ago
Unsupervised decoding of encoded reasoning using language model interpretability Artificial Intelligence	Uncovers how AI thinks, even when hidden.	Anthropic Code	Natural Language Processing (81%)	Score: 2 5 days ago
WaterSearch: A Quality-Aware Search-based Watermarking Framework for Large Language Models Computation and Language	Makes computer writing sound more natural.	Code	Semantic Search (78%)	Score: 2 5 days ago
PanFlow: Decoupled Motion Control for Panoramic Video Generation CV and Pattern Recognition	Creates realistic panoramic videos with smooth, complex motion.	Code 2 Countries	Motion Capture (79%)	Score: 2 5 days ago
DLRREC: Denoising Latent Representations via Multi-Modal Knowledge Fusion in Deep Recommender Systems Information Retrieval	Makes movie suggestions much smarter.	Code	Semantic Search (77%)	Score: 2 6 days ago
ReJump: A Tree-Jump Representation for Analyzing and Improving LLM Reasoning Machine Learning (CS)	Shows how computers "think" to solve problems.	Code	Natural Language Processing (75%)	Score: 2 5 days ago
DrawingBench: Evaluating Spatial Reasoning and UI Interaction Capabilities of Large Language Models through Mouse-Based Drawing Tasks Computation and Language	Tests if AI can follow drawing instructions accurately.	Code	Natural Language Processing (78%)	Score: 2 5 days ago
Toward a benchmark for CTR prediction in online advertising: datasets, evaluation protocols and perspectives Information Retrieval	Tests computer ads to find best ones.	Code	A/B Testing (79%)	Score: 2 5 days ago
HBLLM: Wavelet-Enhanced High-Fidelity 1-Bit Quantization for LLMs Machine Learning (CS)	Makes smart computer programs much smaller.	Code	Quantum Computing (74%)	Score: 2 5 days ago
Efficient Training of Diffusion Mixture-of-Experts Models: A Practical Recipe Machine Learning (CS)	Makes AI image generators work faster and better.	Kuaishou Code	MOOC (76%)	Score: 2 4 days ago
Hybrid-DMKG: A Hybrid Reasoning Framework over Dynamic Multimodal Knowledge Graphs for Multimodal Multihop QA with Knowledge Editing Artificial Intelligence	Helps computers answer questions using text and pictures.	Code 3 Countries	Knowledge Management (77%)	Score: 2 5 days ago
Med-CMR: A Fine-Grained Benchmark Integrating Visual Evidence and Clinical Logic for Medical Complex Multimodal Reasoning Artificial Intelligence	Tests AI's ability to understand medical images and reason.	Code	Image Recognition (77%)	Score: 2 5 days ago