arXiv Machine Learning
Jun 8
Towards Tight Bounds for Streaming Attention
arXiv:2606. 07205v1 Announce Type: cross Abstract: The attention mechanism is a cornerstone of modern transformer architectures.
Inference efficiency
Quantization, distillation, pruning and serving work aimed at the same accuracy for less memory, latency and money.
arXiv AI
Jun 8
On the Geometry of On-Policy Distillation
arXiv:2606. 07082v1 Announce Type: cross Abstract: On-policy distillation (OPD) is increasingly used to improve large language model reasoning, but its training dynamics remain poorly understood.
arXiv AI
Jun 8
Design Once, Deploy at Scale: Template-Driven ML Development for Large Model Ecosystems
arXiv:2603. 24963v3 Announce Type: replace Abstract: Modern computational advertising platforms typically rely on recommendation systems to predict user responses, such as click-through rates, conversion rates, and other optimization events.
arXiv AI
Jun 8
NTILC: Neural Tool Invocation via Learned Compression
arXiv:2606. 06566v1 Announce Type: cross Abstract: Agentic tool-calling language models depend on large registries of callable APIs, functions, and local actions.
arXiv Machine Learning
Jun 8
SEAM: Shortcut-Aware Real-Time Detection of Scripted vs. Spontaneous Speech for Interview Guardrails
arXiv:2606. 06837v1 Announce Type: cross Abstract: Scripted vs spontaneous speech detection is appealing for interview guardrails, but benchmark performance can be inflated by shortcuts tied to corpus identity, channel conditions, and recording artifacts rather than speaking style itself.
arXiv AI
Jun 8
EgoPressDiff: Multimodal Video Diffusion for Egocentric UV-Domain Hand-Pressure Estimation
arXiv:2606. 06872v1 Announce Type: cross Abstract: Estimating hand-surface contact pressure from an egocentric view is crucial for AR/VR devices, robotic imitation, and ergonomic analysis.
arXiv AI
Jun 8
AdMem: Advanced Memory for Task-solving Agents
arXiv:2606. 06787v1 Announce Type: new Abstract: Large Language Models (LLMs) show promise as tool-using agents but remain limited in long-horizon tasks that require remembering, organizing, and reusing knowledge.
arXiv Machine Learning
Jun 8
A Conformation-Centric Generative Foundation Model for Linear Polymer Modeling and Design
arXiv:2510. 16023v2 Announce Type: replace Abstract: Linear polymers, macromolecules formed from monomers covalently bonded into continuous chains, underpin countless technologies and are indispensable to modern life.
arXiv Machine Learning
Jun 8
AI Level of Detail: Distance-Aware ML Model Precision Selection for Real-Time Human Motion Prediction in Games
arXiv:2606. 06565v1 Announce Type: cross Abstract: Modern game engines spend significant compute animating NPCs with learned motion models.
arXiv Machine Learning
Jun 8
Deployed trusted-node quantum key distribution over 300 km with a multi-core fiber access link
arXiv:2606. 06107v1 Announce Type: cross Abstract: Quantum key distribution (QKD) is increasingly considered for deployment in realistic communication networks, where long distances, heterogeneous fiber infrastructure, and coexistence with classical traffic present substantial challenges.
arXiv Machine Learning
Jun 8
Sparsely gated tiny linear experts
arXiv:2606. 07414v1 Announce Type: new Abstract: Sparsity allows scaling model parameters without proportionally increasing computational cost.
arXiv Machine Learning
Jun 8
Bradley-Terry Rankings for Recommender Systems Across Dataset Taxonomies
arXiv:2606. 07492v1 Announce Type: cross Abstract: The ranking of recommendation algorithms is a challenging problem since model performance is sensitive to dataset characteristics such as sparsity, sequential structure, and scale.
arXiv AI
Jun 8
Perplexity Can Miss SAE Feature Damage Under Quantization
arXiv:2606. 03002v2 Announce Type: replace-cross Abstract: Quantization is a standard path to deploying large language models, and quantized models are typically judged acceptable when perplexity or downstream accuracy remains close to the full-precision original.
arXiv AI
Jun 8
Accelerated Fourier SAT (AFSAT): Fully Realising a GPU-based Symmetric Pseudo-Boolean SAT Solver
arXiv:2606. 06641v1 Announce Type: new Abstract: We present Accelerated Fourier SAT (AFSAT), a GPU-accelerated solver for pseudo-Boolean satisfiability based on continuous local search (CLS).
arXiv AI
Jun 8
ActQuant: Sub-4-bit Action-Guided Quantization for Vision-Language-Action Models
arXiv:2605. 24011v2 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models exhibit remarkable action generation for embodied intelligence, but their heavy compute make deployment on edge platforms impractical.
arXiv AI
Jun 8
Data-Efficient Autoregressive-to-Diffusion Language Models via On-Policy Distillation
arXiv:2606. 06712v1 Announce Type: cross Abstract: We study the transformation of autoregressive models (ARLMs) into diffusion language models (DLMs).
arXiv AI
Jun 8
SS-TPT: Stability and Suitability-Guided Test-Time Prompt Tuning for Adversarially Robust Vision-Language Models
arXiv:2606. 06943v1 Announce Type: cross Abstract: Vision-language models (VLMs) such as CLIP achieve strong zero-shot recognition but remain highly fragile under adversarial perturbations.
arXiv AI
Jun 8
E2Former-V2: On-the-Fly Equivariant Attention with Linear Activation Memory
arXiv:2601. 16622v2 Announce Type: replace-cross Abstract: Equivariant Graph Neural Networks (EGNNs) have become a widely used approach for modeling 3D atomistic systems.
arXiv Machine Learning
Jun 8
AAAC: Activation-Aware Adaptive Codebooks for 4-bit LLM Weight Quantization
arXiv:2605. 08692v2 Announce Type: replace Abstract: Post-training weight-only quantization to 4 bits is widely used to reduce the memory and compute costs of large language model inference.
arXiv Machine Learning
Jun 8
Unsupervised Continual Clustering via Forward-Backward Knowledge Distillation
arXiv:2606. 07474v1 Announce Type: new Abstract: Unsupervised Continual Learning (UCL) aims to enable neural networks to learn sequential tasks without labels or access to past data.