AI/ML arXiv cs.AI

A Descriptive and Normative Theory of Human Beliefs in RLHF

Proposes a theory on how human beliefs about agent capabilities influence preferences in RLHF, suggesting new best practices for practitioners.

AI/ML arXiv cs.AI

All Explanations are Wrong, But Many Are Useful: Exploring the Rashomon Explanation Set with Large Language Models

Researchers introduce RashomonLLM, an agentic workflow that uses a set of faithful explanations to improve both the accuracy and explainability of machine learning models.

AI/ML arXiv cs.AI

What VGGT Knows About Overlap: Probing Geometric Foundation Models for Co-Visibility

The Co-VGGT model leverages the internal representations of the VGGT foundation model to efficiently classify co-visibility for 3D reconstruction and robotic localization.

Software Engineering arXiv cs.AI

Failure as a Process: An Anatomy of CLI Coding Agent Trajectories

An empirical study of CLI coding agents reveals that failures are primarily driven by epistemic errors that occur early in the process and often remain hidden until they are unrecoverable.

AI/ML arXiv cs.AI

Seeing is Free, Speaking is Not: Uncovering the True Energy Bottleneck in Edge VLM Inference

Energy profiling of edge VLMs reveals that output token generation, rather than visual processing, is the dominant driver of energy consumption and latency.

AI/ML arXiv cs.AI

ALICE: Learning a General-Purpose Pathology Foundation Model from Vision, Vision-Language, and Slide-Level Experts

ALICE is a unified pathology foundation model created through multi-stage agglomerative distillation from multiple vision and vision-language teacher models.

AI/ML arXiv cs.AI

TCLA: Training-Free Class-wise Logit Adaptation for Medical Vision-Language Models

TCLA is a training-free few-shot adaptation method for Medical Vision-Language Models that improves performance on out-of-distribution data by correcting inference logits.

Other arXiv cs.AI

Large-Scale Portfolio Optimization Problem Under Cardinality Constraint With Enhanced Multi-Objective Evolutionary Algorithms

The paper proposes enhanced multi-objective evolutionary algorithms to solve large-scale portfolio optimization problems under cardinality constraints in financial markets.

AI/ML arXiv cs.AI

Conceptual Networks for Cross-Linguistic Idiomatic Expressions:A Feature-Based Graph Approach

Researchers propose a feature-based graph approach using conceptual networks to represent idiomatic expressions across diverse languages, improving cross-lingual transfer.

AI/ML arXiv cs.AI

PAC-ACT: Post-training Actor-Critic for Action Chunking Transformers

PAC-ACT is a reinforcement-learning post-training framework for Action Chunking Transformers that improves stability and safety in industrial robot contact manipulation.

AI/ML arXiv cs.AI

Task-Specific Multimodal Question Answering Agents via Confidence Calibration and Incremental Reasoning for QANTA 2026

A task-specific two-agent architecture utilizing confidence calibration and incremental reasoning achieved top results in the QANTA 2026 multimodal question answering challenge.

Other Hacker News

The console wars have been lost

A Hacker News discussion regarding the perceived end of competitive console gaming eras.

Other The Verge

This free Mac app reveals the truth about your mystery USB-C cables

A free macOS utility called WhatCable that identifies USB-C cable capabilities using Apple Silicon data.

AI/ML arXiv cs.AI

On-Device Adaptive Battery Power Prediction for Electric Vehicles

Research on on-device adaptive power prediction models for electric vehicles to handle distribution shifts.

AI/ML arXiv cs.AI

Self-Guided Test-Time Training for Long-Context LLMs

Introduction of Self-Guided Test-Time Training (S-TTT) to improve long-context reasoning in LLMs.

AI/ML arXiv cs.AI

SVF-CR: Synchronized Visual-Facial Cross-Refinement for Multimodal Ambivalence and Hesitancy Recognition

A multimodal framework (SVF-CR) for recognizing subtle behavioral states like ambivalence and hesitancy.

AI/ML arXiv cs.AI

A Sovereign, Open-Source Foundation Model for German and English

Release of Soofi S 30B-A3B, an open-source MoE Mamba Transformer model optimized for German and English.

AI/ML arXiv cs.AI

Test-Time Scaling for Small VLMs on Multilingual Visual MCQ

An analysis of how test-time scaling impacts small vision-language models on multilingual benchmarks.

AI/ML arXiv cs.AI

Parameter-Efficient Vision-Language Adaptation with Continuous Metadata Conditioning for Animal Re-Identification

A parameter-efficient CLIP adaptation framework designed for long-term animal re-identification.

Cybersecurity arXiv cs.AI

Practical Source Code Recovery from Binary Functions Using Anchor-Based Retrieval and LLM Reasoning

A pipeline for recovering source code from stripped binary functions using LLM reasoning and anchor retrieval.