arXiv AI
Jul 24
Robostral Navigate
arXiv:2607. 20785v1 Announce Type: cross Abstract: Deploying navigation systems at scale requires a recipe that minimizes sensor assumptions, generalizes across robot embodiments, and trains efficiently.
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
Jul 24
When Does Recurrence Become an Algorithm? Convergence Selection in Weight-Tied Looped Transformers
arXiv:2607. 20594v1 Announce Type: cross Abstract: When does a weight-tied looped transformer -- one block applied T times -- implement an actual algorithm?
arXiv AI
Jul 24
MIRROR: Learning from the Other View for Multi-Modal Reasoning
arXiv:2607. 21552v1 Announce Type: new Abstract: Unlike large language models (LLMs) that exhibit strong reasoning capabilities, vision-language models (VLMs) struggle with visual reasoning, even on geometry problems that admit equivalent text, diagram, and combined diagram+text views.
arXiv AI
Jul 24
Frontier Financial Judgement: Can agents tell what might move a stock?
arXiv:2607. 20645v1 Announce Type: cross Abstract: We introduce Frontier Financial Judgement, a challenging new benchmark developed in collaboration with professional equity analysts to assess agents' ability to replicate expert human judgements.
arXiv AI
Jul 24
Geometric Configurations of Perturbed Jailbreak Prompts
arXiv:2607. 20581v1 Announce Type: cross Abstract: Perturbation techniques that turn unsuccessful jailbreak prompts into successful ones are continuously evolving, constituting a major security threat to LLM safety.
arXiv AI
Jul 24
LinearARD: Linear-Memory Attention Distillation for RoPE Restoration
arXiv:2604. 00004v2 Announce Type: replace-cross Abstract: The extension of context windows in Large Language Models is typically facilitated by scaling positional encodings followed by lightweight Continual Pre-Training (CPT).
arXiv AI
Jul 24
SOAP, Muon, and Beyond: Pushing LLM Pretraining Scales
arXiv:2607. 20548v1 Announce Type: cross Abstract: Higher-order optimizers such as Muon and SOAP offer faster convergence than AdamW, but their computational cost and numerical stability challenges have limited adoption at scale.
arXiv AI
Jul 24
Attention Degradation, Function Token Anchoring, and the Limits of Attention-Based Intervention in Large Language Models
arXiv:2607. 20524v1 Announce Type: new Abstract: Mean cross-positional attention degradation is widely reported in transformer interpretability, yet whether it causally limits contextual retrieval remains untested.
arXiv AI
Jul 24
ConfidenceBench: Evaluating Confidence Calibration in Large Language Models
arXiv:2607. 20526v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed in settings where fluent but incorrect answers can be costly.
arXiv AI
Jul 24
NVIDIA-labs OO Agents: Native Python Object-Oriented Agents
arXiv:2607. 20709v1 Announce Type: new Abstract: Traditional agent development is split across prompt templates, tool schemas, callback code, and workflow graphs.
arXiv AI
Jul 24
Scaling Closed-Loop Feature Channel Configuration with LLMs
arXiv:2607. 20516v1 Announce Type: cross Abstract: Promising initial results in closed-loop large-language-model-based channel-configuration search demonstrated that neural-network widths can be optimized directly through executable code generation and accuracy feedback.
arXiv AI
Jul 24
Verifier-First Evaluation of Agentic LLMs for Infrastructure-as-Code Generation
arXiv:2607. 20478v1 Announce Type: cross Abstract: Infrastructure-as-Code (IaC) generation from natural language requires satisfying provider schemas, dependency planning, and organizational policy constraints, not merely producing syntactically plausible configurations.
arXiv AI
Jul 24
Enhancing Explainable Cardiac Diagnosis with Guide-Grounded Multimodal LLMs
arXiv:2607. 20814v1 Announce Type: new Abstract: The electrocardiogram (ECG) is a cornerstone of cardiac as- sessment, yet clinical deployment of deep learning models remains con- strained by limited interpretability and the hallucination risk of large language models (LLMs).
arXiv Machine Learning
Jul 24
DataPrep-Bench: Benchmarking LLMs as Training Data Preparators
arXiv:2607. 20465v1 Announce Type: new Abstract: The quality of training data fundamentally determines the capabilities of large language models (LLMs), yet no unified benchmark exists to measure how well LLMs, agents, and data-centric workflows actually prepare training data end to end.
arXiv AI
Jul 24
ExecuGraph: A Multi-Agent, Execution-Grounded Framework for Reliable Backend Code Synthesis with Large Language Models
arXiv:2607. 20499v1 Announce Type: new Abstract: Large Language Models generate plausible backend code, but a single-pass paradigm provides no guarantee of correctness or runtime reliability.
arXiv AI
Jul 24
The Devil is in the Spectrum: Mitigating Representation Collapse in LLMs via Topologically Regularized Side-Path
arXiv:2607. 20484v1 Announce Type: new Abstract: Large Language Models (LLMs) are fundamentally limited by representation collapse, a bottleneck that severely degrades long-context performance.
arXiv AI
Jul 24
Marking the Wrong Symptoms: Evaluating LLM Watermarks in Medical Texts
arXiv:2607. 20462v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly integrated into clinical workflows, stressing the need for reliable traceability of model-generated output with watermarking.
arXiv AI
Jul 24
VPWEM: Non-Markovian Visuomotor Policy with Working and Episodic Memory
arXiv:2603. 04910v2 Announce Type: replace-cross Abstract: Imitation learning from human demonstrations has achieved significant success in robotic control, yet most visuomotor policies still condition on single-step observations or short-context histories, making them struggle with non-Markovian tasks that require long-term memory.
arXiv AI
Jul 24
Learn2Zinc: Fine-tuning Small Language Models for Text-to-Model Translation in MiniZinc
arXiv:2607. 20456v1 Announce Type: cross Abstract: Large language models excel at code generation for mainstream programming languages but struggle with rare, domain-specific languages such as MiniZinc, a constraint modeling language for combinatorial problems.
arXiv AI
Jul 24
AISE-Bench: A Full-Cycle Curated Benchmark for Information Seeking on Academic Knowledge Graphs
arXiv:2607. 20498v1 Announce Type: new Abstract: Large language models (LLMs) augmented with tools are emerging as autonomous agents capable of using Web engine, APIs, and code to solve complex, long-horizon tasks.