Shared Lexical Task Representations Explain Behavioral Variability In LLMs
arXiv:2604.22027v1 Announce Type: cross Abstract: One of the most common complaints about large language models (LLMs) is their prompt sensitivity…
Causal Concept Graphs in LLM Latent Space for Stepwise Reasoning
arXiv:2603.10377v2 Announce Type: replace-cross Abstract: Sparse autoencoders can localize where concepts live in language models, but not how they interact…
Pre-trained Large Language Models Learn Hidden Markov Models In-context
arXiv:2506.07298v3 Announce Type: replace-cross Abstract: Hidden Markov Models (HMMs) are foundational tools for modeling sequential data with latent Markovian structure,…
Unlocking the Edge deployment and ondevice acceleration of multi-LoRA enabled one-for-all foundational LLM
arXiv:2604.18655v2 Announce Type: replace-cross Abstract: Deploying large language models (LLMs) on smartphones poses significant engineering challenges due to stringent constraints…
SOLAR-RL: Semi-Online Long-horizon Assignment Reinforcement Learning
arXiv:2604.22558v1 Announce Type: cross Abstract: As Multimodal Large Language Models (MLLMs) mature, GUI agents are evolving from static interactions to…
VLAA-GUI: Knowing When to Stop, Recover, and Search, A Modular Framework for GUI Automation
arXiv:2604.21375v2 Announce Type: replace-cross Abstract: Autonomous GUI agents face two fundamental challenges: early stopping, where agents prematurely declare success without…
Math Takes Two: A test for emergent mathematical reasoning in communication
arXiv:2604.21935v1 Announce Type: new Abstract: Although language models demonstrate remarkable proficiency on mathematical benchmarks, it remains unclear whether this reflects…
Hidden Failure Modes of Gradient Modification under Adam in Continual Learning, and Adaptive Decoupled Moment Routing as a Repair
arXiv:2604.22407v1 Announce Type: cross Abstract: Many continual-learning methods modify gradients upstream (e.g., projection, penalty rescaling, replay mixing) while treating Adam…