multilayer perceptron
PulseAugur coverage of multilayer perceptron — every cluster mentioning multilayer perceptron across labs, papers, and developer communities, ranked by signal.
- instance of Gotit.pub 70%
- used by CatalyzeX Code Finder for Papers 70%
- used by Gotit.pub 70%
- used by IArxiv 70%
- used by magnetic resonance imaging 70%
- instance of CatalyzeX Code Finder for Papers 70%
- instance of IArxiv Recommender 70%
- instance of IArxiv 70%
- instance of PatchTST 70%
- used by AlphaEarth 70%
- competes with Diffusion Transformer 70%
- used by Influence Flower 60%
15 day(s) with sentiment data
-
New system improves map label placement with ML and optimization
Researchers have developed LABELSENSE-Pilot, a prototype system designed to improve the placement of point-feature labels on interactive maps. This system addresses challenges related to geometric validity, display yiel…
-
New method steers AI self-play to specific game equilibria
Researchers have developed a method to steer self-play algorithms towards specific Nash equilibria in two-player zero-sum games. By manipulating a reference policy, the system can be guided to select a desired equilibri…
-
New research questions retrieval benefits in time series forecasting · 2 sources tracked
Two new research papers explore the effectiveness of retrieval-augmented methods for time series forecasting. The first paper introduces a method that learns to predict which historical data points are most relevant for…
-
New framework enables zero-shot cross-lingual sign language handshape recognition
Researchers have developed a novel zero-shot cross-lingual framework for recognizing sign language handshapes, enabling the transfer of knowledge from high-resource languages like American Sign Language (ASL) to low-res…
-
Grokking in Transformers is Spectral Recoding, Not Module Switch
Researchers have identified that the transition from memorization to generalization in Transformer models, a phenomenon known as grokking, is not due to a module switch but rather a spectral recoding of existing distrib…
-
New attack manipulates LLM pricing agents by altering market data presentation
Researchers have developed a new attack method called Market Signal Injection (MSI) that manipulates Large Language Model (LLM) pricing agents by altering the presentation of market data, rather than its numerical value…
-
evMLP: New event-driven MLP architecture for efficient vision processing
Researchers have introduced evMLP, a novel all-MLP architecture designed for vision tasks, particularly video processing. This architecture leverages an event-driven mechanism that processes only changed regions between…
-
Machine learning models accelerate semiconductor defect analysis
Researchers have developed machine learning models to predict defect formation energies and zero-phonon lines in semiconductors, specifically for 4H-SiC. These models aim to accelerate high-throughput workflows by actin…
-
QSTAR framework enhances quantum transfer learning by selectively routing uncertain predictions
Researchers have developed QSTAR, a novel framework for quantum transfer learning that selectively routes uncertain predictions to a quantum branch. This approach aims to clarify the utility of quantum components in mac…
-
New PPDL framework forecasts user retention for short-video platforms
Researchers have developed PPDL, a new framework designed to forecast user retention ratios for large-scale short-video platforms. This framework addresses challenges such as channel heterogeneity, global decay and satu…
-
New research tackles PINN limitations for solving PDEs · 4 sources tracked
Recent research explores advancements in physics-informed neural networks (PINNs) for solving partial differential equations (PDEs). One paper introduces a physics-informed random feature method to address spectral bias…
-
New research reveals how LLMs develop harmful intent, introducing 'Herald' moderator
Researchers have identified "Harmfulness Propagation Dynamics" (HPD), a phenomenon where the representation of harmful intent in large language models increases with the model's depth. This suggests that harmfulness is …
-
New research questions AI's ability to learn compositional features
Researchers have proposed a new method to evaluate whether AI systems truly learn compositional structures from data, rather than just interpolating between existing data points. This approach is crucial for achieving o…
-
New decoding framework tackles LLM hallucinations with internal signals
Researchers have developed DescaPE, a novel decoding framework designed to combat hallucinations in large language models. This method utilizes internal model signals to identify and suppress generation paths prone to f…
-
AquaCubeAI enables on-board satellite turbidity monitoring
Researchers have developed AquaCubeAI, a lightweight machine-learning model designed for onboard estimation of coastal water turbidity using data from the Φsat-2 satellite. This approach aims to reduce latency by proces…
-
New method deciphers feature flow in foundation models
Researchers have developed a new method to understand how foundation models evolve through fine-tuning and editing, focusing on the internal computations of sparse autoencoders (SAEs). By constructing a transition atlas…
-
New research quantifies and repairs reweighting errors in AI rankers
A new research paper introduces the concept of "odds-shift slippage" to describe errors in one-vs-rest rankers caused by reweighting techniques used to handle imbalanced datasets. The study analyzes how these weights, i…
-
ActMap method quantifies LLM uncertainty from single generation
Researchers have developed ActMap, a novel method for quantifying uncertainty in large language models from a single generation. ActMap compresses a model's internal activation trajectory into a compact tensor, which ca…
-
DINO-Med framework adapts DINOv3 for medical imaging analysis · 2 sources tracked
Researchers have developed DINO-Med, a novel framework for adapting natural image foundation models like DINOv3 to multi-modal medical image analysis, specifically for liver fibrosis staging. The framework employs a uni…
-
Field Converter framework improves 3D player pose estimation from soccer broadcasts
Researchers have developed a new framework called Field Converter for estimating 3D player poses from soccer broadcasts. This method uses camera and pitch geometry to initialize player positions in a shared world coordi…