arXiv AI
Jul 22
MUX: Continuous Reasoning via Multiplexed Tokens
arXiv:2607. 18264v1 Announce Type: new Abstract: Language models solve complex problems by articulating intermediate reasoning steps in natural language.
Inference efficiency
Quantization, distillation, pruning and serving work aimed at the same accuracy for less memory, latency and money.
arXiv Machine Learning
Jul 22
CircuitKIT : Circuit Discovery, Evaluation, and Application Toolkit for Mechanistic Interpretability
arXiv:2607. 19317v1 Announce Type: new Abstract: Circuit analysis can support not only model explanation but also downstream interventions such as pruning, editing, steering, and selective fine-tuning.
arXiv Machine Learning
Jul 22
Vectorizing the Trie: Efficient Constrained Decoding for LLM-based Generative Retrieval on Accelerators
arXiv:2602. 22647v2 Announce Type: replace-cross Abstract: Generative retrieval has emerged as a powerful paradigm for LLM-based recommendation.
arXiv AI
Jul 22
Circuit Claims Depend on What Is Extracted and How It Is Compared
arXiv:2607. 18921v1 Announce Type: cross Abstract: Circuit extraction identifies a small set of model components whose presence preserves a target behavior under ablation, and the resulting circuit is often read as the mechanism behind that behavior.
arXiv Machine Learning
Jul 22
Survival of the Cheapest: Cost-Aware Hardware Adaptation for Adversarial Robustness
arXiv:2409. 07609v3 Announce Type: replace-cross Abstract: Deploying adversarially robust machine learning systems requires continuous trade-offs between robustness, cost, and latency.
arXiv Machine Learning
Jul 22
QScheduler: Adaptive Gradient Sampling for Zeroth-Order On-Device Training on INT8 NPUs
arXiv:2607. 18802v1 Announce Type: new Abstract: Zeroth-Order (ZO) optimization enables On-Device Learning (ODL) on NPU-equipped microcontrollers by estimating gradients through forward passes alone, bypassing the need for backpropagation primitives and reducing memory requirements.
arXiv Machine Learning
Jul 22
One Student, Many Teachers: Multi-Task On-Policy Distillation via Soft-Prompt Privileged Context
arXiv:2607. 18293v1 Announce Type: new Abstract: On-policy self-distillation (OPSD) teaches large language models new skills through a teacher that shares the student's backbone and supervises its own rollouts.
arXiv AI
Jul 22
State Compression in Two-Agent LLM Relays: A Closed-World Study of Constraint Preservation
arXiv:2607. 18265v1 Announce Type: new Abstract: Long-running Large Language Model (LLM)-based agents often accumulate large intermediate traces containing audits, eliminations, and numeric calculations.
arXiv AI
Jul 22
Intelligent Multi-UAV Navigation in ITNTNs: A Hierarchical LLM Approach
arXiv:2607. 18604v1 Announce Type: cross Abstract: The deployment of high-speed Uncrewed Aerial Vehicles (UAVs) in 3D aerial highways necessitates robust coordination of physical flight kinematics and multi-tier network handovers.
arXiv AI
Jul 22
OpenRTAG: A Comprehensive Benchmark for Robust Text-Attributed Graph Learning under Data Quality Degradation
arXiv:2607. 19108v1 Announce Type: new Abstract: Text-attributed graphs (TAGs) are an important graph data form that combine relational structure with rich node text.
arXiv AI
Jul 22
Breaking the MoE LLM Trilemma: Dynamic Expert Clustering with Structured Compression
arXiv:2510. 02345v4 Announce Type: replace-cross Abstract: Mixture-of-Experts (MoE) Large Language Models (LLMs) face a trilemma of load imbalance, parameter redundancy, and communication overhead.
arXiv Machine Learning
Jul 22
HindsightBench: A Black-Box Behavioral Audit Protocol for Parametric Hindsight in Time-Indexed LLM Decision Tasks
arXiv:2607. 18867v1 Announce Type: new Abstract: Large language models leak parametric knowledge of realized outcomes into historical financial decision tasks.
arXiv Machine Learning
Jul 22
AdaFlash: Adaptive Speculative Decoding via On-Policy Distilled Diffusion Drafters
arXiv:2607. 19223v1 Announce Type: new Abstract: Speculative decoding, in which a lightweight draft model first generates a draft sequence that is then verified in parallel by the target model, has become a prevalent paradigm for accelerating large language model inference.
arXiv Machine Learning
Jul 22
Contraction-Gauge Preconditioning for Quantized Matrix Multiplication
arXiv:2607. 18745v1 Announce Type: new Abstract: We study low-precision computation of C=AB with both factors quantized.
arXiv AI
Jul 22
FinRAG-12B: A Production-Validated Recipe for Grounded Question Answering in Banking
arXiv:2605. 05482v2 Announce Type: replace Abstract: Large language models (LLMs) are rapidly being adopted across various domains.
arXiv Machine Learning
Jul 22
Generalized Least Squares Kernelized Tensor Factorization
arXiv:2412. 07041v4 Announce Type: replace-cross Abstract: Recovering incomplete multidimensional tensor-structured data is a fundamental task in many real-world applications.
arXiv AI
Jul 22
Beyond Single-Dimensional Compression: The Compound Sparsity Frontier of Large Language Models
arXiv:2607. 18280v1 Announce Type: cross Abstract: Large language models (LLMs) are often compressed through static parameter pruning or dynamic token-level computation, yet aggressive sparsification can trigger rapid performance degradation beyond an essential sparsity boundary.
arXiv Machine Learning
Jul 22
SHUFFLESPARSE: Learned Shuffles for Structured Sparse Networks
arXiv:2510. 14812v2 Announce Type: replace Abstract: Structured weight sparsity accelerates training and inference on modern GPUs, but it trails unstructured dynamic sparse training (DST) in accuracy especially at extreme sparsity.
arXiv Machine Learning
Jul 22
Exposure-Based Reinforcement Learning to Rank
arXiv:2607. 18689v1 Announce Type: new Abstract: Reinforcement learning (RL) methods for learning-to-rank (LTR) can optimize (almost) any ranking goal, e.
arXiv AI
Jul 22
Trajectory-Aware Clinical Risk Prediction via Severity-Grounded Knowledge Graphs and Retrieval-Augmented Generation
arXiv:2607. 18270v1 Announce Type: new Abstract: While Electronic Health Records (EHRs) offer a wealth of clinical data, effectively augmenting a patient's records with heterogeneous external knowledge to predict the patient's clinical risk remains a significant challenge.