AIBullisharXiv – CS AI · May 287/10
🧠Researchers propose a novel direct training algorithm for Spiking Neural Networks that addresses performance gaps with traditional ANNs through circulate-firing neurons, learnable surrogate gradients, and balanced loss functions. The method demonstrates competitive results across datasets and extends effectively to Transformer architectures, potentially advancing energy-efficient neural network applications.
AIBullisharXiv – CS AI · May 127/10
🧠LoopVLA introduces a recurrent Vision-Language-Action model architecture that learns when to stop refining representations for robotic control tasks, achieving 45% parameter reduction and 1.7x faster inference while maintaining or improving task performance. The model uses self-supervised learning to estimate representation sufficiency rather than relying on predefined layer depths or heuristic rules.
AIBearisharXiv – CS AI · May 127/10
🧠Researchers identify Refusal-Escape Directions (RED) as mathematical perturbation vectors that explain why aligned LLMs remain vulnerable to jailbreaks. The study reveals structural vulnerabilities arise from fundamental trade-offs between safety mechanisms and model utility, with normalization and residual connections as key exploitable components.
AIBullisharXiv – CS AI · May 117/10
🧠Researchers introduce LaProx, a novel KV Cache eviction strategy for long-context LLM inference that reformulates the problem from head-wise weight averaging to output-aware layer-wise matrix multiplication. The method achieves 2× accuracy loss reduction under extreme compression while maintaining performance with just 5% of the original KV cache.
AIBullisharXiv – CS AI · May 97/10
🧠Researchers introduce Leviathan, a Transformer architecture that decouples input embeddings from output projections using learned embedding vectorization (LEV), achieving 9% perplexity reduction at 1.2B parameters with minimal overhead. The approach concentrates improvements on rare tokens while requiring 2.1x fewer training tokens to match baseline performance.
🏢 Perplexity
AIBearisharXiv – CS AI · May 97/10
🧠Researchers have identified a critical architectural flaw in large vision-language models: attention mechanisms are largely redundant and misallocate computational resources, with random attention weights performing comparably to learned ones. This finding challenges fundamental assumptions about Transformer design and suggests current LVLMs inefficiently process visual information despite their scale.
AIBullisharXiv – CS AI · Mar 127/10
🧠Researchers have developed a new scaling law for Mixture-of-Experts (MoE) models that optimizes compute allocation between expert and attention layers. The study extends the Chinchilla scaling law by introducing an optimal ratio formula that follows a power-law relationship with total compute and model sparsity.
AINeutralarXiv – CS AI · Mar 117/10
🧠Researchers introduce 'opaque serial depth' as a metric to measure how much reasoning large language models can perform without externalizing it through chain of thought processes. The study provides computational bounds for Gemma 3 models and releases open-source tools to calculate these bounds for any neural network architecture.
AIBullisharXiv – CS AI · Mar 57/10
🧠Researchers developed ELMUR, a new AI architecture that uses external memory to help robots make better decisions over extremely long time periods. The system achieved 100% success on tasks requiring memory of up to one million steps and nearly doubled performance on robotic manipulation tasks compared to existing methods.
AIBullisharXiv – CS AI · Mar 47/102
🧠Researchers propose SUN (Shared Use of Next-token Prediction), a novel approach for multi-LLM serving that enables cross-model sharing of decode execution by decomposing transformers into separate prefill and decode modules. The system achieves up to 2.0x throughput improvement per GPU while maintaining accuracy comparable to full fine-tuning, with a quantized version (QSUN) providing additional 45% speedup.
AIBullisharXiv – CS AI · Mar 37/104
🧠Researchers introduce Uni-X, a novel architecture for unified multimodal AI models that addresses gradient conflicts between vision and text processing. The X-shaped design uses modality-specific processing at input/output layers while sharing middle layers, achieving superior efficiency and matching 7B parameter models with only 3B parameters.
$UNI
AIBullisharXiv – CS AI · Mar 37/103
🧠Researchers developed NextHAM, a deep learning method for predicting electronic-structure Hamiltonians of materials, offering significant computational efficiency advantages over traditional DFT methods. The system introduces neural E(3)-symmetry architecture and a new dataset Materials-HAM-SOC with 17,000 material structures spanning 68 elements.
AIBullishOpenAI News · Apr 237/105
🧠Researchers have developed the Sparse Transformer, a deep neural network that achieves new performance records in sequence prediction for text, images, and sound. The model uses an improved attention mechanism that can process sequences 30 times longer than previously possible.
AINeutralarXiv – CS AI · Jun 236/10
🧠Researchers present Enactor, a generative AI model designed to simulate vehicle behavior at signalized intersections with improved accuracy over existing methods. The model uses transformer-based architecture to predict vehicle trajectories in closed-loop simulations, achieving significantly better performance on safety metrics and traffic flow distribution compared to baseline approaches.
AINeutralarXiv – CS AI · Jun 236/10
🧠MoECodec introduces a unified image compression framework using Mixture-of-Experts (MoE) routing to dynamically adapt compression based on image content and downstream vision tasks. The approach reduces computational overhead compared to task-specific models while maintaining performance across multiple machine perception applications.
AINeutralarXiv – CS AI · Jun 236/10
🧠Researchers introduce ACTIVA, a transformer-based variational autoencoder designed to estimate causal interventional distributions from observational data without requiring intervention datasets. The model amortizes causal knowledge across tasks, enabling zero-shot inference and outperforming existing baselines on synthetic and biological datasets while reducing spurious correlations.
AINeutralarXiv – CS AI · Jun 236/10
🧠Researchers introduce Temporal Graph Pattern Machine (TGPM), a foundation framework that learns generalized evolving patterns in dynamic networks using Transformer architecture and self-supervised pre-training. The model achieves top performance on temporal link prediction and node classification tasks while demonstrating strong cross-domain transferability, addressing limitations of existing task-centric approaches.
AINeutralarXiv – CS AI · Jun 235/10
🧠Researchers propose a FiLM-coordinated dual-branch Transformer architecture that separates global and local dependency modeling in language models, using feature-wise linear modulation for dynamic cross-branch coordination. The approach demonstrates consistent improvements over single-branch baselines in small-scale language modeling benchmarks while maintaining parameter efficiency through intelligent channel-wise calibration rather than token-level interaction.
AINeutralarXiv – CS AI · Jun 236/10
🧠Researchers introduce SOHET, a transformer-based architecture for processing heterogeneous event streams with self-supervised pre-training capabilities. The model demonstrates significant performance improvements on fraud detection and sequential prediction tasks, outperforming existing methods by 5.8% on a large-scale benchmark while achieving faster convergence.
AINeutralarXiv – CS AI · Jun 236/10
🧠Researchers present JPPD, a joint prediction-planning diffusion framework that treats autonomous vehicle trajectory planning and pedestrian prediction as a single coupled problem rather than sequential steps. The approach uses differentiable safety guidance and conditional flow matching to improve safety metrics and runtime efficiency in shared-space transportation environments like sidewalks and pedestrian zones.
AIBullisharXiv – CS AI · Jun 116/10
🧠Researchers present a transformer-based framework for non-contact heart-rate estimation using RGB cameras, addressing the challenge of varying illumination conditions. The system achieves 0.79 bpm mean absolute error and 0.982 correlation on illumination-varied datasets, significantly outperforming existing baselines and enabling practical physiological sensing for service robots.
AINeutralarXiv – CS AI · Jun 106/10
🧠Researchers propose a CNN-Transformer hybrid architecture for Arabic Speech Emotion Recognition that achieves 98.1% accuracy, outperforming CNN-LSTM and fine-tuned wav2vec 2.0 models. The study addresses the underexplored challenge of emotion detection in Arabic speech by combining convolutional feature extraction with Transformer-based context modeling, demonstrating effectiveness in low-resource, dialectally diverse settings.
AINeutralarXiv – CS AI · Jun 106/10
🧠Researchers propose EEG-TransNet, a transformer-based deep learning architecture that combines ResNet preprocessing, local self-attention mechanisms, and a novel Fuzzy-Attention Synchronous Transformer to improve EEG-based emotion recognition and brain activity classification. The model demonstrates superior performance across three datasets with better generalization across subjects and robustness to varying signal lengths.
AINeutralarXiv – CS AI · Jun 106/10
🧠Researchers introduce CITRAS, a Transformer-based model that improves time series forecasting by effectively integrating multiple data types: target variables, observed covariates (past-only data), and known covariates (advance-known data like calendar events). The model addresses a critical limitation in existing deep learning forecasting systems through two novel mechanisms that align future covariate information with predictions and refine cross-variable dependencies.
AINeutralarXiv – CS AI · Jun 96/10
🧠Researchers have developed AQIFormer, a transformer-based AI system that estimates air quality from traffic camera imagery combined with weather data. The model achieves 89.96% accuracy on training data and maintains strong cross-city generalization with 81.67% accuracy on independent Indian datasets, significantly outperforming existing methods.
