arXiv AI
Aug 6
OneDayAgent: Towards a Long-Horizon Harness for Autonomous Agents
arXiv:2608. 05013v1 Announce Type: cross Abstract: LLM agents are increasingly applied to open-ended everyday requests that span work, study, and life.
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 Machine Learning
Aug 6
MALT: Lightweight Curvature-Aware Muon via Diagonal Preconditioning
arXiv:2608. 05088v1 Announce Type: new Abstract: Muon has recently emerged as a promising alternative to AdamW for language model pretraining by orthogonalizing momentum matrices using Newton-Schulz iterations.
arXiv AI
Aug 6
What We Observe as LLM Behavior Can Be a Side-effect of Inference Backend
arXiv:2608. 04714v1 Announce Type: cross Abstract: Benchmark scores are reported as properties of a model, yet the inference framework used to produce them, such as HuggingFace, vLLM, or Ollama, are considered non-influential and their names and versions are almost never disclosed.
arXiv AI
Aug 6
Protoreasoning in Tiny Transformers
arXiv:2608. 04980v1 Announce Type: cross Abstract: We show that tiny transformers can profitably employ a simple form of Chain of Thought, which we call protoreasoning, allowing us to study step-by-step reasoning on ~1M-parameter models and opening up opportunities for much more detailed experimentation and analysis than is feasible for larger models.
arXiv AI
Aug 6
RepairFormer: Automated Repair of Structured Inputs Using Transformers
arXiv:2608. 05060v1 Announce Type: cross Abstract: Structured input files such as JSON, DOT, OBJ, INI, S-expression, and TinyC are widely used in software systems, but small corruptions can cause parsers to reject otherwise useful data.
arXiv AI
Aug 6
Instruction-Conditioned Exploration for Reinforcement Learning with Self-Distillation to an Unconditioned Policy
arXiv:2608. 02087v2 Announce Type: replace Abstract: Post-training Large Language Models (LLMs) with Reinforcement Learning (RL) has become an important tool for improving model capabilities, but the LLM action-space structure introduces challenges distinct from classical RL, with implications for inducing exploration.
arXiv AI
Aug 6
Large-Small Model Collaboration for Enhancing Edge-Deployed Small Models
arXiv:2503. 10367v2 Announce Type: replace-cross Abstract: Edge devices host domain-specific small language models (SLMs) with limited resources, while private clouds offer larger LLMs.
arXiv AI
Aug 6
COMPAS: Difficulty-Aware Joint Search for Optimizing Code Generation
arXiv:2608. 04336v1 Announce Type: cross Abstract: Code generation systems make each LLM call with a model, a prompt, and decoding settings.
arXiv AI
Aug 6
Can Post-Training Transform LLMs into Causal Reasoners?
arXiv:2602. 06337v2 Announce Type: replace-cross Abstract: Causal inference is essential for decision-making but remains challenging for non-experts.
arXiv AI
Aug 6
CIDR: A Large-Scale Industrial Source Code Dataset for Software Engineering Research
arXiv:2605. 12153v2 Announce Type: replace-cross Abstract: We present the Curated Industrial Developer Repository (CIDR), a large-scale dataset of real-world software repositories collected from industrial partners.
arXiv Machine Learning
Aug 6
Attention-Only White-Box Transformer via LeJEPA-Based Self-Supervised Pretraining
arXiv:2608. 04213v1 Announce Type: new Abstract: Existing studies on self-supervised learning for white-box networks typically decouple the derivation of white-box networks via optimization algorithms from self-supervised learning paradigms.
arXiv AI
Aug 6
Patients-like-me: A Variational LM--GNN Framework for Explainable Clinical Prediction
arXiv:2608. 04193v1 Announce Type: cross Abstract: Language models (LMs) offer strong textual representations for electronic health records (EHRs), but they encode patient sequences in isolation and provide limited explainability.
arXiv Machine Learning
Aug 6
Attention, Anomalies! Handling Attention Layers in Unsupervised Federated Outlier Detection
arXiv:2608. 04753v1 Announce Type: new Abstract: Attention layers are the backbone of today's most powerful and impactful models.
arXiv AI
Aug 6
MERaLiON-GR: Speech Gender Recognition Model for English and SEA Languages
arXiv:2608. 04433v1 Announce Type: cross Abstract: We present MERaLiON-GR, a speech gender recognition system that performs binary classification (female / male) on English and Southeast Asian (SEA) languages.
arXiv AI
Aug 6
Explicit Language Memory for Long-Horizon Planning in Vision-Language-Action Models
arXiv:2608. 04765v1 Announce Type: cross Abstract: Vision-language-action (VLA) models provide a unified paradigm for connecting visual perception, language understanding, and robotic control.
arXiv Machine Learning
Aug 6
The Neural Echo: A Signal Processing Perspective for Understanding Neural Networks
arXiv:2608. 04864v1 Announce Type: cross Abstract: We introduce the neural echo as a tool for understanding the behavior of neural networks.
arXiv AI
Aug 6
When does training on downscaled images yield the same gradients?
arXiv:2608. 04448v1 Announce Type: cross Abstract: Diffusion transformers deliver strong image generation, but their training cost grows superlinearly with resolution.
arXiv AI
Aug 6
When Absence Is Evidence: Evaluating Completeness-Sensitive Negative Reasoning in Large Language Models
arXiv:2608. 04591v1 Announce Type: cross Abstract: Large language models (LLMs) are often asked whether something is absent from a record, list, or retrieved context.
arXiv AI
Aug 6
The Effect of Perceived Race and Gender on Police Language Use: Experimental Evidence from VR Simulations
arXiv:2608. 05050v1 Announce Type: cross Abstract: Against the backdrop of violence in police interactions with the U.
arXiv AI
Aug 6
Corrigibility Transformation: Constructing Goals That Accept Updates
arXiv:2510. 15395v2 Announce Type: replace Abstract: An AI agent will learn a desired goal more effectively if it does not resist the training process, but many partially learned goals incentivize an AI to avoid further goal updates.