IsalProgram is a regular assembly-like language where all instruction strings are valid programs executed on a circular doubly linked list VM without addresses or variable names.
hub
Advances in Neural Information Processing Systems , volume =
15 Pith papers cite this work. Polarity classification is still indexing.
15
Pith papers citing it
hub tools
years
2026 15representative citing papers
Proves that RoPE attention loses locality bias and token distinction in long contexts, approaching random behavior independent of content.
A new VLA model called SI uses a four-step chain-of-thought to derive driving intent and applies it via classifier-free guidance to a flow-matching trajectory generator, showing competitive Waymo scores and intent-controllable plans.
LWDrive uses future-frame supervision on VLMs to create world-model features that a multi-layer Foresight Cascade Planner refines into final trajectories, reporting 92.0 on NAVSIM and 89.6 on NAVSIM-v2.
Mean-field theory of dropout at the edge of chaos derives scaling laws showing front-loaded schedules outperform constant dropout by shifting the perfect-alignment fixed point.
NeuroMAS reframes multi-agent language systems as neural architectures where LLM agents learn coordination via reinforcement learning rather than predefined roles.
ReflectDrive-2 combines masked discrete diffusion with RL-aligned self-editing to generate and refine driving trajectories, reaching 91.0 PDMS on NAVSIM camera-only and 94.8 in best-of-6.
Omni-Flow introduces a three-layer abstraction (Control Flow, Data Flow, Compute Flow) for unified orchestration and KV cache sharing in multimodal inference pipelines.
A self-supervised JEPA model on nuPlan data uses temporal prediction error to score driving scenario complexity without labels, assigning higher scores to turns and pedestrian interactions and achieving AP 0.512 in anomaly detection.
UTOPYA fuses eight modalities via FiLM-conditioned attention and physics-informed regularization to reach AUROC 0.874 for anomaly detection in batch distillation, outperforming baselines by 0.147.
CKT-WAM transfers teacher WAM knowledge to students via compressed text-embedding contexts using LQCA and adapters, reaching 86.1% success on LIBERO-Plus with 1.17% trainable parameters and 83.3% in real-world tasks.
Benchmarking in pediatric ICU antimicrobial stewardship shows performance depends mainly on target prevalence and dataset traits rather than model complexity, with sequence models improving precision-recall at 24-hour resolution but showing poorer calibration than tabular models.
Authors call for contamination-resistant LLM benchmarks that exploit Transformer training-inference asymmetry and require new mathematical methods for cross-architecture interoperability.
citing papers explorer
-
The IsalProgram Programming Language
IsalProgram is a regular assembly-like language where all instruction strings are valid programs executed on a circular doubly linked list VM without addresses or variable names.
-
RoPE Distinguishes Neither Positions Nor Tokens in Long Contexts, Provably
Proves that RoPE attention loses locality bias and token distinction in long contexts, approaching random behavior independent of content.
-
Action Emergence from Streaming Intent
A new VLA model called SI uses a four-step chain-of-thought to derive driving intent and applies it via classifier-free guidance to a flow-matching trajectory generator, showing competitive Waymo scores and intent-controllable plans.
-
LWDrive: Layer-Wise World-Model-Guided Vision-Language Model Planning for Autonomous Driving
LWDrive uses future-frame supervision on VLMs to create world-model features that a multi-layer Foresight Cascade Planner refines into final trajectories, reporting 92.0 on NAVSIM and 89.6 on NAVSIM-v2.
-
Dropout Universality: Scaling Laws and Optimal Scheduling at the Edge-of-Chaos
Mean-field theory of dropout at the edge of chaos derives scaling laws showing front-loaded schedules outperform constant dropout by shifting the perfect-alignment fixed point.
-
NeuroMAS: Multi-Agent Systems as Neural Networks with Joint Reinforcement Learning
NeuroMAS reframes multi-agent language systems as neural architectures where LLM agents learn coordination via reinforcement learning rather than predefined roles.
-
ReflectDrive-2: Reinforcement-Learning-Aligned Self-Editing for Discrete Diffusion Driving
ReflectDrive-2 combines masked discrete diffusion with RL-aligned self-editing to generate and refine driving trajectories, reaching 91.0 PDMS on NAVSIM camera-only and 94.8 in best-of-6.
-
Omni-Flow: A Unified Workflow Orchestration and Distributed KV Cache Sharing Framework for Multimodal Inference
Omni-Flow introduces a three-layer abstraction (Control Flow, Data Flow, Compute Flow) for unified orchestration and KV cache sharing in multimodal inference pipelines.
-
Zero-Label Driving Scenario Complexity Detection via Joint Embedding Predictive Architecture
A self-supervised JEPA model on nuPlan data uses temporal prediction error to score driving scenario complexity without labels, assigning higher scores to turns and pedestrian interactions and achieving AP 0.512 in anomaly detection.
-
UTOPYA: A Multimodal Deep Learning Framework for Physics-Informed Anomaly Detection and Time-Series Prediction
UTOPYA fuses eight modalities via FiLM-conditioned attention and physics-informed regularization to reach AUROC 0.874 for anomaly detection in batch distillation, outperforming baselines by 0.147.
-
CKT-WAM: Parameter-Efficient Context Knowledge Transfer Between World Action Models
CKT-WAM transfers teacher WAM knowledge to students via compressed text-embedding contexts using LQCA and adapters, reaching 86.1% success on LIBERO-Plus with 1.17% trainable parameters and 83.3% in real-world tasks.
-
Benchmarking Machine Learning Architectures for Antimicrobial Stewardship in Pediatric ICUs
Benchmarking in pediatric ICU antimicrobial stewardship shows performance depends mainly on target prevalence and dataset traits rather than model complexity, with sequence models improving precision-recall at 24-hour resolution but showing poorer calibration than tabular models.
-
LLM Benchmark Datasets Should Be Contamination-Resistant
Authors call for contamination-resistant LLM benchmarks that exploit Transformer training-inference asymmetry and require new mathematical methods for cross-architecture interoperability.
- VISHC at PsyDefDetect: Mitigating Data Scarcity in Psychological Defense Classification with Context-Aware Synthetic Augmentation
- IConFace: Fine-Grained Identity Conditioning for Reference-Aware Face Restoration