AIBullisharXiv – CS AI · 3d ago7/10
🧠Researchers introduce NEXT, a neural network method that estimates external joint torques on robot arms without dedicated force sensors, paired with FIRST, a training technique that improves policy learning by 17% across long-horizon tasks. This breakthrough enables cost-effective force-aware teleoperation and manipulation on commodity robots by leveraging only 10 minutes of free-motion calibration data.
AIBullisharXiv – CS AI · 6d ago7/10
🧠ActQuant introduces a novel post-training quantization framework that compresses Vision-Language-Action models to sub-4-bit weights while maintaining 94-95% performance, enabling practical deployment on edge devices. The method combines action-guided bit allocation with curvature-aware optimization, achieving 5.3× compression on major VLA models and validated performance on physical robotic hardware.
AIBullisharXiv – CS AI · Jun 47/10
🧠Researchers introduce LiftQuant, a novel quantization framework enabling continuous bit-width control for Large Language Models by lifting weights into higher-dimensional space and projecting them back via 1-bit lattices. The approach bridges the gap between rigid integer bit-widths and real-world deployment constraints, allowing a 70B LLM to compress to 2.4 bits while maintaining hardware efficiency and outperforming existing 2-bit quantization methods.
AIBullisharXiv – CS AI · Jun 47/10
🧠Researchers introduce SSSD, a training-free method for accelerating Large Language Model inference that reduces latency by up to 2.9x through n-gram matching and hardware-aware speculation. The approach matches performance of existing trained methods while eliminating deployment complexity, data preparation, and maintenance overhead.
AINeutralarXiv – CS AI · Jun 17/10
🧠Researchers demonstrate that restructuring communication topology in multi-robot systems yields significantly larger performance improvements than scaling individual model sizes, with hierarchical interaction design improving performance by 47 points versus 9 points from doubling neural network capacity. This finding challenges the conventional focus on model scaling in AI systems and suggests interaction architecture may be equally or more critical for coordinated multi-agent performance.
AIBullisharXiv – CS AI · Jun 17/10
🧠Researchers demonstrate that large language models can effectively forecast GPU kernel performance, reducing expensive on-device evaluations during optimization searches. By acting as selective surrogates that know their confidence limits, LLMs enable kernel searches to evaluate multiple candidates under fixed GPU budgets, ultimately discovering faster kernels than baseline approaches.
AIBullisharXiv – CS AI · May 287/10
🧠Researchers introduce CIVIC, a framework that optimizes Vision-Language Models by maintaining compact visual token sequences throughout the entire inference pipeline, reducing KV-cache memory to one-third while achieving measurable hardware acceleration without accuracy loss.
AIBullisharXiv – CS AI · May 287/10
🧠Researchers propose Group-Query Latent Attention (GQLA), an advancement of DeepSeek's Multi-head Latent Attention that enables hardware-adaptive decoding through two algebraically equivalent inference paths without requiring model retraining. The innovation allows a single trained model to optimize performance across different hardware platforms—H100 GPUs and export-restricted H20 chips—while maintaining computational efficiency and supporting distributed tensor parallelism.
AIBullisharXiv – CS AI · May 117/10
🧠Researchers introduce SpikingBrain, a family of brain-inspired large language models optimized for efficient long-context processing on non-NVIDIA hardware. The models achieve comparable performance to Transformers while requiring significantly fewer tokens for training, delivering up to 100x speedup for long sequences and 69% sparsity for low-power operation.
🏢 Nvidia
AIBullisharXiv – CS AI · Apr 207/10
🧠Researchers have developed AscendKernelGen, an LLM-based framework that dramatically improves code generation for neural processing units (NPUs) by combining domain-specific training data with reinforcement learning. The system achieves 95.5% compilation success on complex kernels, up from near-zero baseline performance, addressing a critical bottleneck in AI hardware optimization.
🏢 Hugging Face
AIBullisharXiv – CS AI · Apr 157/10
🧠Researchers present OSC, a hardware-efficient framework that addresses the challenge of deploying Large Language Models with 4-bit quantization by intelligently separating activation outliers into a high-precision processing path while maintaining low-precision computation for standard values. The technique achieves 1.78x speedup over standard 8-bit approaches while limiting accuracy degradation to under 2.2% on state-of-the-art models.
AIBullisharXiv – CS AI · Apr 137/10
🧠Researchers introduce Ge²mS-T, a novel Spiking Vision Transformer architecture that optimizes energy efficiency while maintaining training and inference performance through multi-dimensional grouped computation. The approach addresses fundamental limitations in existing SNN paradigms by balancing memory overhead, learning capability, and energy consumption simultaneously.
AIBullisharXiv – CS AI · Apr 107/10
🧠Researchers present a new approach to General Matrix Multiplication (GEMM) using Space Filling Curves that automatically optimizes data movement across memory hierarchies without requiring platform-specific tuning. The method achieves up to 5.5x speedups over vendor libraries and demonstrates significant performance gains in LLM inference and distributed computing applications.
AIBullisharXiv – CS AI · Mar 127/10
🧠Researchers have identified a simple solution to training instability in 4-bit quantized large language models by removing mean bias, which causes the dominant spectral anisotropy. This mean-subtraction technique substantially improves FP4 training performance while being hardware-efficient, potentially enabling more accessible low-bit LLM training.
AIBullisharXiv – CS AI · Mar 117/10
🧠Researchers have developed two software techniques (OAS and MBS) that dramatically improve MXFP4 quantization accuracy for Large Language Models, reducing the performance gap with NVIDIA's NVFP4 from 10% to below 1%. This breakthrough makes MXFP4 a viable alternative while maintaining 12% hardware efficiency advantages in tensor cores.
🏢 Nvidia
AINeutralarXiv – CS AI · Jun 46/10
🧠Researchers introduce dMX, a differentiable mixed-precision quantization framework that enables dynamic floating-point bit-width assignment across different layers of large language models. The method uses continuous optimization with temperature-based annealing to efficiently compress models while maintaining accuracy, demonstrating improvements over existing quantization heuristics across multiple LLM families.
🏢 Perplexity🧠 Llama
AINeutralarXiv – CS AI · May 96/10
🧠Researchers present Budgeted Attention Allocation, a mechanism that allows a single transformer model to operate at multiple efficiency-accuracy tradeoffs by dynamically gating attention heads based on computational budgets. The approach achieves measurable speedups (1.2-1.28x) on CPU benchmarks while maintaining competitive accuracy across multiple datasets, enabling flexible deployment scenarios without retraining.
AIBullisharXiv – CS AI · May 96/10
🧠Researchers propose FRE-RNN, a brain-inspired recurrent neural network that improves Equilibrium Propagation (EP), a biologically plausible learning framework, by reducing computational costs to match backpropagation performance. The advancement addresses critical instability and efficiency challenges that have limited EP's practical implementation in large-scale neural networks.
AIBullisharXiv – CS AI · Apr 146/10
🧠Researchers introduce AEG, a bare-metal runtime framework that enables high-performance machine learning inference on heterogeneous AI accelerators without OS overhead. The system achieves 9.2× higher compute efficiency and uses 11× fewer hardware tiles than Linux-based alternatives, demonstrating significant potential for edge AI deployment optimization.
AIBullisharXiv – CS AI · Feb 276/108
🧠Researchers propose GRAU, a new reconfigurable activation unit design for neural network hardware accelerators that uses piecewise linear fitting with power-of-two slopes. The design reduces LUT consumption by over 90% compared to traditional multi-threshold activators while supporting mixed-precision quantization and nonlinear functions.
GeneralNeutralMIT Technology Review · May 114/10
📰The article examines how charger technology has undergone significant improvements over the past decade, becoming smaller, safer, and faster through various technological innovations. While less visible than advances in smartphones or wearables, these improvements represent meaningful progress in power delivery infrastructure that affects consumer experience across all portable devices.
