AI/ML arXiv cs.AI

In-context learning of closed form solution to simple linear regression task using transformer with linear self-attention

This paper demonstrates that transformers with linear self-attention can in-context learn the closed-form least squares estimate for simple linear regression using layer normalization.

Hardware/Chips arXiv cs.AI

RTL-Sequencer: Towards Scalable RTL Timing Prediction with the Sequence-based Paradigm

RTL-Sequencer is a new sequence-based paradigm for scalable RTL timing prediction that linearizes logic cones to improve early-stage timing optimization.

AI/ML arXiv cs.AI

CAMMAR: Culture-Aware Matryoshka for Metaphorical Arabic Representations

CAMMAR is a representation learning framework designed to separate lexical, cultural, and metaphorical meanings in Arabic language models to prevent 'semantic smearing'.

AI/ML arXiv cs.AI

Test-Time Noise Guided Adaptation for Realistic Autoregressive Video Generation

TANGO is introduced to prevent error accumulation in autoregressive video generation by using the diffusion model as a critic of its own noise distribution.

Software Engineering arXiv cs.AI

Agentic Synthesis against Counterexample-Supplemented Sketches

The authors propose a repository-native method for coding agents to learn policies through counterexample-supplemented sketches, reducing rework in software synthesis.

AI/ML arXiv cs.AI

Conditional Reliability of Toxicity Signals for Multilingual and Code-Mixed Abuse Detection

ToxGate is a trust-fusion head proposed to improve multilingual and code-mixed abuse detection by treating external toxicity signals as conditional evidence.

AI/ML arXiv cs.AI

EgoExoMoCap: Distributed Ego-Exo Human Motion Capture

EgoExoMoCap is a distributed framework for human motion capture using smart glasses, combining egocentric and exocentric signals for 3D motion reconstruction.

AI/ML Hacker News

1-Bit LLM in the Browser

A discussion on implementing 1-Bit Large Language Models (LLMs) directly in the browser, focusing on extreme quantization for efficiency.

AI/ML arXiv cs.AI

On the Structure of Address in Multi-Party Dialogue: From Discrete Labels to Continuous Levels

Research on treating addressee detection in multi-party dialogues as a continuous phenomenon rather than discrete labels to improve turn-taking prediction.

AI/ML arXiv cs.AI

Toward a mechanistic understanding of inference in visual cortex and diffusion models

A model bridging neuroscience and ML by describing perceptual inference in the visual cortex as a minimal diffusion model based on sparse coding.

AI/ML arXiv cs.AI

Efficient Difficulty-Aware Dynamic Routing for Diffusion-Based Real-World Image Super-Resolution

Introduction of a Difficulty-aware Dynamic Routing (DDR) strategy for image super-resolution to optimize efficiency by matching network capacity to image difficulty.

AI/ML arXiv cs.AI

Map as a Prompt: Learning Multi-Modal Spatial-Signal Foundation Models for Cross-scenario Wireless Localization

SigMap, a multimodal foundation model for wireless localization using a 'map-as-prompt' framework to improve cross-scenario adaptation in 5G/6G.

AI/ML arXiv cs.AI

Debiasing Text-to-Image Evaluation via Implicit Cultural Alignment Reward Modeling

A lightweight 4.2B parameter MLLM reward model designed to debias text-to-image evaluation by aligning with implicit cultural norms.

AI/ML arXiv cs.AI

AuEmoChat: Authentic Emotion Understanding and Rendering for Conversational Speech Synthesis

AuEmoChat, a CSS framework using discrete emotion tokens and flow matching to create more authentic emotional conversational speech synthesis.

AI/ML arXiv cs.AI

GeoChrono: Benchmarking and Rethinking Long-Term Temporal Understanding in Remote Sensing

GeoChrono and ChronoBench, an MLLM and benchmark for long-term temporal understanding in remote sensing of Earth's surface evolution.

AI/ML arXiv cs.AI

Scaling Time Series Classification via XAI-Driven Data Reduction

drXAI, a methodology that uses XAI attribution methods for data reduction in time series classification to enable scaling of resource-intensive models.

AI/ML arXiv cs.AI

AquaAugmentor: A Novel Feature Augmentation Algorithm for Water Potability Prediction

AquaAugmentor, a feature augmentation algorithm designed to improve water potability prediction in low-dimensional datasets.

AI/ML arXiv cs.AI

Ask Twice, Look Twice: Prompt Echoing Resolves the Question-First Paradox in Vision-Language Models

Researchers propose 'question echoing' to resolve a paradox in VLMs where placing the question after the image improves performance, despite intuition suggesting the opposite.

AI/ML arXiv cs.AI

Information-Directed Sampling for Causal Bandits

A new Bayesian framework for causal bandits is introduced to improve reward estimation in systems with non-manipulable variables.

AI/ML arXiv cs.AI

MemoGuard: An Adaptive Runtime for Guarding Against Memory Traps in Communication-Limited Robot Navigation

MemoGuard is a lightweight adaptive runtime that prevents memory traps in communication-limited robot navigation by validating episodic memories before reuse.