Thinking Machines Lab inks massive compute deal with Nvidia
The multi-year deal involves at least a gigawatt of compute power and also includes a strategic investment from Nvidia.
Google gives in to users’ complaints over AI-powered ‘Ask Photos’ search feature
The option appears on the Google Photos Search screen and lets users pick which experience they want.
Sandbar secures $23M Series A for its AI note-taking ring
Sandbar aims to ship the Stream, which can be used to take notes, chat with an AI assistant, and for media playback, this summer.
Elaborating a Human Rights-Friendly Copyright Framework for Generative AI
Validation of a Small Language Model for DSM-5 Substance Category Classification in Child Welfare Records
arXiv:2603.06836v1 Announce Type: new Abstract: Background: Recent studies have demonstrated that large language models (LLMs) can perform binary classification tasks on child welfare narratives, detecting the presence or absence of constructs such as substance-related problems, domestic violence, and firearms involvement....
Reforming the Mechanism: Editing Reasoning Patterns in LLMs with Circuit Reshaping
arXiv:2603.06923v1 Announce Type: new Abstract: Large language models (LLMs) often exhibit flawed reasoning ability that undermines reliability. Existing approaches to improving reasoning typically treat it as a general and monolithic skill, applying broad training which is inefficient and unable to...
Counting on Consensus: Selecting the Right Inter-annotator Agreement Metric for NLP Annotation and Evaluation
arXiv:2603.06865v1 Announce Type: new Abstract: Human annotation remains the foundation of reliable and interpretable data in Natural Language Processing (NLP). As annotation and evaluation tasks continue to expand, from categorical labelling to segmentation, subjective judgment, and continuous rating, measuring agreement...
Hierarchical Embedding Fusion for Retrieval-Augmented Code Generation
arXiv:2603.06593v1 Announce Type: new Abstract: Retrieval-augmented code generation often conditions the decoder on large retrieved code snippets. This ties online inference cost to repository size and introduces noise from long contexts. We present Hierarchical Embedding Fusion (HEF), a two-stage approach...
Hierarchical Latent Structures in Data Generation Process Unify Mechanistic Phenomena across Scale
arXiv:2603.06592v1 Announce Type: new Abstract: Contemporary studies have uncovered many puzzling phenomena in the neural information processing of Transformer-based language models. Building a robust, unified understanding of these phenomena requires disassembling a model within the scope of its training. While...
A Coin Flip for Safety: LLM Judges Fail to Reliably Measure Adversarial Robustness
arXiv:2603.06594v1 Announce Type: new Abstract: Automated \enquote{LLM-as-a-Judge} frameworks have become the de facto standard for scalable evaluation across natural language processing. For instance, in safety evaluation, these judges are relied upon to evaluate harmfulness in order to benchmark the robustness...
Deep Research, Shallow Evaluation: A Case Study in Meta-Evaluation for Long-Form QA Benchmarks
arXiv:2603.06942v1 Announce Type: new Abstract: Recent advances have made long-form report-generating systems widely available. This has prompted evaluation frameworks that use LLM-as-judge protocols and claim verification, along with meta-evaluation frameworks that seek to validate these methods. Many of the meta-evaluations...
AutoChecklist: Composable Pipelines for Checklist Generation and Scoring with LLM-as-a-Judge
arXiv:2603.07019v1 Announce Type: new Abstract: Checklists have emerged as a popular approach for interpretable and fine-grained evaluation, particularly with LLM-as-a-Judge. Beyond evaluation, these structured criteria can serve as signals for model alignment, reinforcement learning, and self-correction. To support these use...
Hit-RAG: Learning to Reason with Long Contexts via Preference Alignment
arXiv:2603.07023v1 Announce Type: new Abstract: Despite the promise of Retrieval-Augmented Generation in grounding Multimodal Large Language Models with external knowledge, the transition to extensive contexts often leads to significant attention dilution and reasoning hallucinations. The surge in information density causes...
Enhancing Consistency of Werewolf AI through Dialogue Summarization and Persona Information
arXiv:2603.07111v1 Announce Type: new Abstract: The Werewolf Game is a communication game where players' reasoning and discussion skills are essential. In this study, we present a Werewolf AI agent developed for the AIWolfDial 2024 shared task, co-hosted with the 17th...
Emotion Transcription in Conversation: A Benchmark for Capturing Subtle and Complex Emotional States through Natural Language
arXiv:2603.07138v1 Announce Type: new Abstract: Emotion Recognition in Conversation (ERC) is critical for enabling natural human-machine interactions. However, existing methods predominantly employ categorical or dimensional emotion annotations, which often fail to adequately represent complex, subtle, or culturally specific emotional nuances....
Scaling Self-Supervised Speech Models Uncovers Deep Linguistic Relationships: Evidence from the Pacific Cluster
arXiv:2603.07238v1 Announce Type: new Abstract: Similarities between language representations derived from Self-Supervised Speech Models (S3Ms) have been observed to primarily reflect geographic proximity or surface typological similarities driven by recent expansion or contact, potentially missing deeper genealogical signals. We investigate...
Taiwan Safety Benchmark and Breeze Guard: Toward Trustworthy AI for Taiwanese Mandarin
arXiv:2603.07286v1 Announce Type: new Abstract: Global safety models exhibit strong performance across widely used benchmarks, yet their training data rarely captures the cultural and linguistic nuances of Taiwanese Mandarin. This limitation results in systematic blind spots when interpreting region-specific risks...
RILEC: Detection and Generation of L1 Russian Interference Errors in English Learner Texts
arXiv:2603.07366v1 Announce Type: new Abstract: Many errors in student essays can be explained by influence from the native language (L1). L1 interference refers to errors influenced by a speaker's first language, such as using stadion instead of stadium, reflecting lexical...
Domain-Specific Quality Estimation for Machine Translation in Low-Resource Scenarios
arXiv:2603.07372v1 Announce Type: new Abstract: Quality Estimation (QE) is essential for assessing machine translation quality in reference-less settings, particularly for domain-specific and low-resource language scenarios. In this paper, we investigate sentence-level QE for English to Indic machine translation across four...
The Dual-Stream Transformer: Channelized Architecture for Interpretable Language Modeling
arXiv:2603.07461v1 Announce Type: new Abstract: Standard transformers entangle all computation in a single residual stream, obscuring which components perform which functions. We introduce the Dual-Stream Transformer, which decomposes the residual stream into two functionally distinct components: a token stream updated...
Cross-Modal Taxonomic Generalization in (Vision-) Language Models
arXiv:2603.07474v1 Announce Type: new Abstract: What is the interplay between semantic representations learned by language models (LM) from surface form alone to those learned from more grounded evidence? We study this question for a scenario where part of the input...
Skip to the Good Part: Representation Structure & Inference-Time Layer Skipping in Diffusion vs. Autoregressive LLMs
arXiv:2603.07475v1 Announce Type: new Abstract: Autoregressive (AR) language models form representations incrementally through left-to-right prediction, whereas diffusion language models (dLLMs) are trained via full-sequence denoising. Although recent dLLMs match AR performance, it remains unclear whether diffusion objectives fundamentally reshape internal...
A Joint Neural Baseline for Concept, Assertion, and Relation Extraction from Clinical Text
arXiv:2603.07487v1 Announce Type: new Abstract: Clinical information extraction (e.g., 2010 i2b2/VA challenge) usually presents tasks of concept recognition, assertion classification, and relation extraction. Jointly modeling the multi-stage tasks in the clinical domain is an underexplored topic. The existing independent task...
Bolbosh: Script-Aware Flow Matching for Kashmiri Text-to-Speech
arXiv:2603.07513v1 Announce Type: new Abstract: Kashmiri is spoken by around 7 million people but remains critically underserved in speech technology, despite its official status and rich linguistic heritage. The lack of robust Text-to-Speech (TTS) systems limits digital accessibility and inclusive...
TableMind++: An Uncertainty-Aware Programmatic Agent for Tool-Augmented Table Reasoning
arXiv:2603.07528v1 Announce Type: new Abstract: Table reasoning requires models to jointly perform semantic understanding and precise numerical operations. Most existing methods rely on a single-turn reasoning paradigm over tables which suffers from context overflow and weak numerical sensitivity. To address...
Learning-free L2-Accented Speech Generation using Phonological Rules
arXiv:2603.07550v1 Announce Type: new Abstract: Accent plays a crucial role in speaker identity and inclusivity in speech technologies. Existing accented text-to-speech (TTS) systems either require large-scale accented datasets or lack fine-grained phoneme-level controllability. We propose a accented TTS framework that...
Nw\=ach\=a Mun\=a: A Devanagari Speech Corpus and Proximal Transfer Benchmark for Nepal Bhasha ASR
arXiv:2603.07554v1 Announce Type: new Abstract: Nepal Bhasha (Newari), an endangered language of the Kathmandu Valley, remains digitally marginalized due to the severe scarcity of annotated speech resources. In this work, we introduce Nw\=ach\=a Mun\=a, a newly curated 5.39-hour manually transcribed...
Whitening Reveals Cluster Commitment as the Geometric Separator of Hallucination Types
arXiv:2603.07755v1 Announce Type: new Abstract: A geometric hallucination taxonomy distinguishes three failure types -- center-drift (Type~1), wrong-well convergence (Type~2), and coverage gaps (Type~3) -- by their signatures in embedding cluster space. Prior work found Types~1 and~2 indistinguishable in full-dimensional contextual...
QuadAI at SemEval-2026 Task 3: Ensemble Learning of Hybrid RoBERTa and LLMs for Dimensional Aspect-Based Sentiment Analysis
arXiv:2603.07766v1 Announce Type: new Abstract: We present our system for SemEval-2026 Task 3 on dimensional aspect-based sentiment regression. Our approach combines a hybrid RoBERTa encoder, which jointly predicts sentiment using regression and discretized classification heads, with large language models (LLMs)...
Scaling Data Difficulty: Improving Coding Models via Reinforcement Learning on Fresh and Challenging Problems
arXiv:2603.07779v1 Announce Type: new Abstract: Training next-generation code generation models requires high-quality datasets, yet existing datasets face difficulty imbalance, format inconsistency, and data quality problems. We address these challenges through systematic data processing and difficulty scaling. We introduce a four-stage...