arXiv Machine Learning
Aug 12
Off-Axis, On Purpose: Where a Transformer Computes Concepts and Why it Does So
arXiv:2608. 10251v1 Announce Type: cross Abstract: A transformer's answer lives on one axis: the direction its unembedding reads.
Large language models
Model releases, architecture work and prompting research on large language models — from frontier-lab announcements to the arXiv papers behind them.
arXiv AI
Aug 12
Predicting Space Groups of Double Perovskites by LLM with Dynamic Few-Shot Learning
arXiv:2608. 10483v1 Announce Type: new Abstract: Double perovskites (DPs) offer broad compositional tunability, but predicting the space groups (SGs) of stable structures remains difficult because available datasets are often strongly imbalanced toward dominant SG classes.
arXiv AI
Aug 12
Hierarchical Compositionality for An Assistive AI Agent
arXiv:2608. 10330v1 Announce Type: new Abstract: AI agents are increasingly being developed to assist humans in various applications, and Large Language Models and other deep network architectures are considered to be state of the art for such agents.
arXiv AI
Aug 12
MEGA: Self-Evolving Agent Optimization Infrastructure via Wisdom Graph
arXiv:2608. 10504v1 Announce Type: new Abstract: As coding agents increasingly handle implementation, the central challenge shifts from building individual agents to building an infrastructure that systematically improves them.
arXiv AI
Aug 12
MD-ProTector: Positioning Multiple Data-Driven Prototypes for LLM-Generated Text Detection
arXiv:2608. 10459v1 Announce Type: cross Abstract: As LLM-generated content becomes more sophisticated, detection systems for distinguishing those texts from human-written text must operate at scale while handling diverse writing styles, domains, languages, and generator models.
arXiv AI
Aug 12
MemSpec: Memory-Aware Runtime for Adaptive Draft Scheduling in Speculative Decoding on Edge Devices
arXiv:2608. 10362v1 Announce Type: cross Abstract: Speculative decoding accelerates autoregressive large language model (LLM) inference by using a lightweight draft model to speculate multiple tokens, reducing expensive target model decoding steps.
arXiv AI
Aug 12
Compute-Optimal Is Not Cluster-Optimal: Systems-Aware Scaling for Sparse Mixture-of-Experts
arXiv:2608. 10605v1 Announce Type: cross Abstract: In large-scale pretraining, the algorithm, architecture, and systems decisions are conventionally made in disconnected stages.
arXiv AI
Aug 12
ImpactHO: Importance-Aware KV Cache Transfer for Multi-User Edge LLM Handover
arXiv:2608. 10545v1 Announce Type: cross Abstract: Edge LLMs must preserve inference continuity when a user hands over between edge nodes, requiring key-value (KV) cache transfer to the target node.
arXiv AI
Aug 12
VibeLifeBench: Can Your Life Agent Be Proactive and Persistent in a Living World?
arXiv:2608. 10875v1 Announce Type: cross Abstract: Large language model (LLM) agents are increasingly deployed as personal assistants.
arXiv AI
Aug 12
Attention-Path Fragility as an Uncertainty Signal in Large Language Models
arXiv:2608. 11138v1 Announce Type: cross Abstract: We propose that a model's uncertainty about a token is reflected not only in the breadth of its output distribution but also in whether a confident prediction is \emph{fragile} under perturbation of its attention pathways.
arXiv AI
Aug 12
Diffusion-Based Impedance Learning for Contact-Rich Manipulation Tasks
arXiv:2509. 19696v4 Announce Type: replace-cross Abstract: Learning-based methods excel at robot motion generation but remain limited in contact-rich physical interaction.
arXiv AI
Aug 12
Situation Graph Prediction for User Perspective Modeling
arXiv:2602. 13319v2 Announce Type: replace Abstract: Perspective-aware AI requires modeling evolving internal states---goals, emotions, contexts---not merely preferences.
arXiv AI
Aug 12
InfiniteScienceGym: An Unbounded, Procedurally-Generated Benchmark for Scientific Analysis
arXiv:2604. 13201v2 Announce Type: replace-cross Abstract: Large language models are emerging as scientific assistants, but evaluating their ability to reason from empirical data remains challenging.
arXiv AI
Aug 12
HexEval: An Evidence-Driven Hexagonal Framework for Multidimensional Scholar Assessment
arXiv:2608. 10584v1 Announce Type: new Abstract: Scholar assessment plays a fundamental role in faculty recruitment, funding allocation, academic promotion, and talent discovery.
arXiv AI
Aug 12
From Reasoning Depth to Reasoning Breadth: Evaluating Multi-Point Associative Reasoning in Large Language Models
arXiv:2608. 10444v1 Announce Type: cross Abstract: Large language models (LLMs) have made substantial progress on reasoning tasks that require increasingly long and complex inferential chains.
arXiv AI
Aug 12
INSIDE the Student's Mind: Jointly Modeling Latent Reasoning and Action in LLM Student Simulators
arXiv:2608. 10492v1 Announce Type: new Abstract: Large Language Model (LLM)-based simulators often reproduce observable actions but fail to capture the underlying reasoning behind them.
arXiv Machine Learning
Aug 12
MoE Proxy Models for Low-Cost Failure Reproduction and Diagnosis in LLM RL Post-Training
arXiv:2608. 10823v1 Announce Type: new Abstract: Reinforcement learning (RL) post-training of large language models (LLMs) is computationally intensive and involves complex system pipelines with substantial debugging overhead.
arXiv AI
Aug 12
Optimal Stopping of Self-Refining Foundation Models
arXiv:2608. 10729v1 Announce Type: cross Abstract: Foundation models can improve their outputs through a self-refinement process driven by external feedback.
arXiv AI
Aug 12
TrAC: Trace-Conditioned Answer Consistency for Efficient Uncertainty Quantification in LLMs
arXiv:2608. 00422v2 Announce Type: replace Abstract: Large language models (LLMs) can generate fluent reasoning traces that nevertheless lead to incorrect answers, making response-level uncertainty estimation important for abstention, human review, and adaptive compute allocation.
arXiv Machine Learning
Aug 12
Beyond a Bag of Features: Set-Level Instability in Sparse Autoencoders
arXiv:2608. 11197v1 Announce Type: new Abstract: Shani et al.