arXiv AI
Aug 6
TwinIR: Coordinated Invisible Dual-Point Attacks on Online HD Map Construction
arXiv:2608. 04453v1 Announce Type: cross Abstract: Online HD map construction is critical to prediction and planning in autonomous driving.
Inference efficiency
Quantization, distillation, pruning and serving work aimed at the same accuracy for less memory, latency and money.
arXiv AI
Aug 6
What Is a Skill Worth? Structure-Aware Shapley Valuation of Agent Skills
arXiv:2608. 04562v1 Announce Type: new Abstract: Agent skills are increasingly optimized by automated feedback loops, producing long structured artifacts whose internal value remains unclear.
arXiv AI
Aug 6
CheMLFlow: An Open-Source Platform for Cheminformatics and Materials Informatics Applications
arXiv:2608. 04942v1 Announce Type: cross Abstract: CheMLFlow is an open-source platform for building and executing end-to-end, high-throughput, and agentic workflows for scientific and technological applications.
arXiv Machine Learning
Aug 6
BnBERT-iPET: Sparse Few-Shot Language Modeling for Bengali via Lottery Ticket Pruning
arXiv:2608. 05104v1 Announce Type: new Abstract: Deep neural networks have shown impressive success in NLP tasks owing to their complex structure and huge number of edges.
arXiv AI
Aug 6
Agentic Reinforcement Learning with Observation-Calibrated Self-Distillation
arXiv:2608. 04788v1 Announce Type: cross Abstract: Large language model agents are commonly trained through reinforcement learning with sparse trajectory-level rewards, which offer limited guidance on how strongly individual tokens should be updated.
arXiv AI
Aug 6
SSTQ:Privacy-Preserving Vector Quantization via Subsampled Stochastic TurboQuant
arXiv:2608. 05127v1 Announce Type: cross Abstract: Achieving local differential privacy in distributed optimization while maintaining low communication cost remains challenging.
arXiv Machine Learning
Aug 6
Reward Structure Shapes the Interaction Between Episodic Exploration and Neural Memory in Reinforcement Learning
arXiv:2608. 05111v1 Announce Type: new Abstract: In partially observable reinforcement learning, agents face a dual bottleneck: they must explore to encounter rewarding states and retain that experience in memory to optimize their policies.
arXiv AI
Aug 6
Rethinking Reservoir Pruning: A Dynamical Perspective for Echo State Networks
arXiv:2608. 04593v1 Announce Type: cross Abstract: Echo State Networks (ESNs) offer an efficient framework for temporal prediction, but their randomly initialized reservoirs are often over-parameterized and dynamically redundant.
arXiv Machine Learning
Aug 6
Towards Understanding Gradient Flow Dynamics of Homogeneous Neural Networks Beyond the Origin
arXiv:2502. 15952v3 Announce Type: replace Abstract: Recent works exploring the training dynamics of homogeneous neural network weights under gradient flow with small initialization have established that in the early stages of training, the weights remain small and near the origin, but converge in direction.
arXiv AI
Aug 6
EndoVLM: An Endoscopy Vision-Language Pre-training Model via Anatomy-Guided Sparsity and Progressive Alignment
arXiv:2608. 04472v1 Announce Type: cross Abstract: The development of foundation models (FMs) is crucial for advancing endoscopic image analysis.
arXiv AI
Aug 6
Tropical Algebraic Geometry for Neuronal Representations: An Arakelov-Green Measure Based Descriptor for Graph Learning
arXiv:2608. 04460v1 Announce Type: cross Abstract: The quantitative analysis of 3D neuronal morphologies requires capturing both graph topology and spatial geometry.
arXiv AI
Aug 6
Training-Free Hashing-Based Attention via Binary Principal Components
arXiv:2608. 04405v1 Announce Type: cross Abstract: Long-context large language models (LLMs) are increasingly deployed in real-world applications, yet self-attention remains a major efficiency bottleneck -- especially during decoding -- due to the necessity of repeatedly processing ever-growing key-value (KV) caches.
arXiv AI
Aug 6
CSGen: A Multi-Domain Curvilinear Structure Generation Model via Hierarchical Multimodal Diffusion
arXiv:2608. 04655v1 Announce Type: cross Abstract: Curvilinear structure analysis is an important and fundamental task in multimedia.
arXiv AI
Aug 6
Recurrent Residual Quantization: A Progressive Multi-Precision Representation for LLMs
arXiv:2608. 04048v1 Announce Type: cross Abstract: Serving large language models (LLMs) under diverse deployment constraints requires flexible trade-offs between accuracy, memory footprint, and throughput.
arXiv AI
Aug 6
SPOT: Sparse Probing and Outcome Calibration for On-Policy Distillation
arXiv:2608. 04419v1 Announce Type: cross Abstract: On-policy distillation (OPD) provides dense teacher supervision on student-generated trajectories, but standard reverse-KL training can assign insufficient probability to other plausible continuations.
arXiv AI
Aug 6
OPD-V: Visual On-Policy Self-Distillation with Modality Balance
arXiv:2608. 05131v1 Announce Type: cross Abstract: On-Policy Self-Distillation (OPSD) has become a standard post-training approach for improving visual reasoning in multimodal large language models (MLLMs).
arXiv Machine Learning
Aug 6
DIVE: Dynamic Iterative Visual Evidence Construction for Efficient Vision-Language Models
arXiv:2608. 04496v1 Announce Type: cross Abstract: Visual inputs in vision-language models (VLMs) are often encoded into substantially longer token sequences than text, making visual tokens a major bottleneck for efficient inference.
arXiv AI
Aug 6
LaPrune: Controllable Differentiable Sparsity at Million Scale
arXiv:2608. 04057v1 Announce Type: cross Abstract: Top-$k$ selection determines which components of a sparse model remain active.
arXiv AI
Aug 6
Not Every Divergence Should Be Suppressed: Counterfactual Recoverability in On-Policy Distillation
arXiv:2608. 04408v1 Announce Type: cross Abstract: On-policy distillation (OPD) supervises student-visited trajectories, yet divergence-based rules cannot determine whether an erroneous prefix remains correctable.
arXiv AI
Aug 6
Architectural Implications of Agentic AI Workflows
arXiv:2608. 04458v1 Announce Type: new Abstract: Agentic AI is emerging in datacenters, but its architectural implications remain unexplored.