AI/ML arXiv cs.AI

Artificial Epanorthosis: Why large language models overuse a classical rhetorical figure, and how to mitigate it

A study analyzes the LLM tendency to overuse 'epanorthosis' (self-correction) and proposes mitigation using LoRA adapters and specific instructions.

AI/ML arXiv cs.AI

Improved lower bounds for the Shannon capacity of odd cycles

New lower bounds for the Shannon capacity of odd cycles were discovered using iterative interactions with an LLM for combinatorial construction.

AI/ML arXiv cs.AI

GS-Agent: Creating 4D Physical Worlds With Generative Simulation

GS-Agent is a multi-agent framework that integrates physics engines to generate controllable and physically plausible 4D worlds from natural language.

AI/ML arXiv cs.AI

ElasticTTT: Prior-Preserving Test-Time Tuning for Video Editing

ElasticTTT is a framework designed to prevent 'Prior Collapse' in video editing by preserving the generative distribution of pretrained diffusion models.

Software Engineering arXiv cs.AI

From Resource Flow to Executable Tests: Petri-Net-Guided LLM Test Generation for Concurrent Stateful Rust APIs

A new methodology uses Petri-nets to guide LLMs in generating executable and concurrency-aware tests for stateful Rust APIs.

AI/ML arXiv cs.AI

Visual Contrastive Self-Distillation

Visual Contrastive Self-Distillation (VCSD) improves VLMs by using image-content removal to create a self-distillation signal without needing external teachers.

AI/ML arXiv cs.AI

Beyond Sufficiency: Time Series Explanation with Counterfactual Necessity

TimePNS is a necessity-aware framework for time-series explanation that uses counterfactual interventions to identify truly decision-critical subsequences.

AI/ML arXiv cs.AI

Synthetic data generation framework for quality control automation in gravure printing

A synthetic data generation framework is proposed to automate defect detection in rotogravure printing using RFDETR models trained on synthetic images.

AI/ML arXiv cs.AI

Hilbert Operator for Progressive Encoding (HOPE): A Mathematical Framework for Deconstructing Learned Representations in Deep Networks

The paper introduces HOPE, a mathematical framework that uses Hilbert spaces to unify network pruning and neuron merging for more efficient model compression.

AI/ML arXiv cs.AI

DINOde: Continuous Vision-Text Alignment for Open-Vocabulary Semantic Segmentation

DINOde is an ODE-based framework designed to continuously align CLIP text embeddings with the DINO visual manifold for better open-vocabulary semantic segmentation.

AI/ML arXiv cs.AI

Mean-to-Score Discrete Diffusion: Posterior-Mean Denoisers for Score Entropy

This research introduces Mean-to-Score (M2S), a method to improve discrete diffusion models by ensuring score vectors are Bayes realizable through a posterior-mean prediction mechanism.

AI/ML arXiv cs.AI

VoLN: Vision-Only Long-Horizon Navigation---Paradigm, Benchmark, and Method

The authors propose Vision-Only Long-Horizon Navigation (VoLN), a new paradigm for autonomous agents to navigate using only local in-scene cues rather than external instructions.

AI/ML arXiv cs.AI

When Are Reasoning-Based Guardrails Not Efficient? ResponseGuard: A Fast Vision-Language Guard for Real-Time Moderation

ResponseGuard is a high-speed, single-pass vision-language guardrail that outperforms reasoning-based models in detecting harmfulness with significantly lower latency.

Other arXiv cs.AI

Cycle-Consistent and Uncertainty-Aware Neural Surrogates for Tokamak Edge Plasmas

This work presents cycle-consistent neural surrogates for tokamak edge plasma simulations, enabling real-time control and parameter recovery with high accuracy.

AI/ML arXiv cs.AI

Token Budget Saturation and Mechanistic Early Detection of Reasoning Non-Convergence in Chain-of-Thought Models

The paper explores how the convergence of chain-of-thought reasoning in LLMs can be detected early using linear probes on internal model representations.

AI/ML arXiv cs.AI

Adaptive Identity Anchoring: Closed-Loop Keyframe Placement for Synthetic Paired Supervision in Video Face Swapping

Adaptive Identity Anchoring (AIA) is proposed to improve video face swapping by dynamically placing keyframes to maintain identity stability and texture quality.

AI/ML arXiv cs.AI

RUMBA: Russian User Memory Benchmark

RUMBA is a new benchmark for testing the long-term conversational memory of LLMs, focusing on temporal reasoning and multi-session retrieval in Russian.

Other arXiv cs.AI

Thinkink: 2D Spatial Ink-native Interaction with LLMs

Thinkink is a 2D spatial ink-native interface designed for collaborative ideation between humans and LLMs via handwritten sketches and text.

AI/ML TechCrunch

I tried out OpenAI’s new AI keypad — which will be fun for some coders and slightly mystifying to everyone else

OpenAI has introduced a new AI-powered keypad, designed to assist users with coding and other tasks, though its utility may be limited to a specific subset of users.

Other Ars Technica

Wildfire forces evacuation of NASA's Deep Space Network complex in Spain

A wildfire in Spain has forced the evacuation of NASA's Deep Space Network complex, with damage assessments pending.