Developer Tools B

Showing 211–240 of 408
  • arXiv cs.CL (Computation and Language) · EN Training & Fine-tuning
    FinanceHarness: Autonomous Financial Deep Research Framework
    AI Agents
    Read original (arXiv cs.CL (Computation and Language)) ↗
  • arXiv cs.CL (Computation and Language) · EN New Model Releases
    Beyond Feeling Better: Capability-Sustaining Emotional Dialogue as a Longitudinal Research Paradigm
    Neural Network
    Read original (arXiv cs.CL (Computation and Language)) ↗
  • arXiv cs.CL (Computation and Language) · EN New Model Releases
    AutoSupervision: Closing the Feedback Loop in Scientific Workflows with Grounded Revision Verification
    GPT Retrieval-Augmented Generation (RAG)
    Read original (arXiv cs.CL (Computation and Language)) ↗
  • arXiv cs.CL (Computation and Language) · EN Developer Tools
    MemTxn: A Transaction Boundary for Source-Supported Updates and Complete-State Recovery in Agent Memory
    AI Agents Neural Network Retrieval-Augmented Generation (RAG) Software Engineering
    Read original (arXiv cs.CL (Computation and Language)) ↗
  • arXiv cs.CL (Computation and Language) · EN New Model Releases
    Beyond Borrowed Histories: Person-Aligned User Simulation for Interactive Role-Playing Evaluation
    AI Agents Neural Network
    Read original (arXiv cs.CL (Computation and Language)) ↗
  • arXiv cs.CL (Computation and Language) · EN New Model Releases
    Semantic-Aligned Structural Abstraction for Multimodal Sentiment Analysis
    Retrieval-Augmented Generation (RAG)
    Read original (arXiv cs.CL (Computation and Language)) ↗
  • arXiv cs.CL (Computation and Language) · EN Training & Fine-tuning
    Reasoning Consensus: Structural Ensembling of LLM Reasoning via Weighted DAG Aggregation
    Neural Network Software Engineering
    Read original (arXiv cs.CL (Computation and Language)) ↗
  • arXiv cs.CL (Computation and Language) · EN New Model Releases
    Cocktail-Talker: Multi-Speaker Dialog Modeling in Noisy Social Environments with Turn Action GRPO
    Fine-tuning Reinforcement Learning Speech Processing
    Read original (arXiv cs.CL (Computation and Language)) ↗
  • arXiv cs.CL (Computation and Language) · EN Multimodal
    Can LVLMs Uncover the Truth Behind Visual Illusions? An Analysis of Perceptual and Reasoning Capabilities
    Neural Network Reinforcement Learning Software Engineering
    Read original (arXiv cs.CL (Computation and Language)) ↗
  • arXiv cs.CL (Computation and Language) · EN Safety & Evaluation
    Measuring Alignment With Reader Highlights Net of Position and Length
    Deep Learning Reinforcement Learning
    Read original (arXiv cs.CL (Computation and Language)) ↗
  • arXiv cs.CL (Computation and Language) · EN New Model Releases
    Baikal: Structured Search for Deep Research over Data Lakes
    GPT
    Read original (arXiv cs.CL (Computation and Language)) ↗
  • arXiv cs.CL (Computation and Language) · EN Training & Fine-tuning
    Tight Sample Complexity for Low-Rank Adaptation: Matching Bounds and Rank Selection
    Deep Learning Fine-tuning Machine Learning Software Engineering
    Read original (arXiv cs.CL (Computation and Language)) ↗
  • arXiv cs.CL (Computation and Language) · EN Funding & M&A
    From Single- to Cross-Document: Benchmarking Multi-Granularity Event Analysis of Large Language Models
    Neural Network Retrieval-Augmented Generation (RAG)
    Read original (arXiv cs.CL (Computation and Language)) ↗
  • arXiv cs.CL (Computation and Language) · EN New Model Releases
    Harness-G: A Graph-Structured Harness for Search Agents
    AI Agents Reinforcement Learning Software Engineering
    Read original (arXiv cs.CL (Computation and Language)) ↗
  • ITmedia AI+ · JA Developer Tools extract
    Excel作業を自動化する「Copilot in Excel」がスキルに対応 何ができる?
    'Copilot in Excel' gains skills support to automate spreadsheet work
    Microsoft
    Microsoft strengthened the finance-focused capabilities of Copilot in Excel and added support for 'skills' to automate spreadsheet tasks. The company says its own finance team used and evaluated the feature in production, developing it with the reliability that financial work demands.
    Read original (ITmedia AI+) ↗
  • arXiv cs.CL (Computation and Language) · EN New Model Releases
    ReDiPPO: Reference-Guided Value Calibration and Discrepancy-Aware Token Reweighting for Mathematical Reasoning
    Reinforcement Learning Software Engineering
    Read original (arXiv cs.CL (Computation and Language)) ↗
  • arXiv cs.CL (Computation and Language) · EN Multimodal
    DualAnchor: Preserving Language Priors and Improving Lexical Fidelity in Gloss-Free Sign Language Translation
    Read original (arXiv cs.CL (Computation and Language)) ↗
  • arXiv cs.CL (Computation and Language) · EN Developer Tools
    AWARE-FX: An Auditable Knowledge-Guided AI System for Measuring Corporate Foreign-Exchange Hedging Disclosure
    Machine Learning Neural Network Natural Language Processing (NLP) Reinforcement Learning
    Read original (arXiv cs.CL (Computation and Language)) ↗
  • arXiv cs.CL (Computation and Language) · EN Inference & Efficiency
    Beyond Similarity: Grounded Agentic Extraction and Expert-Adjudicated Evaluation of Intertextuality in Classical Chinese Histories
    Inference Neural Network
    Read original (arXiv cs.CL (Computation and Language)) ↗
  • Apple Machine Learning Research · EN New Model Releases extract
    Dimensionality Reduction Meets Network Science: Sensemaking on UMAP’s kNN Graph
    Apple applies network science to UMAP's kNN graph for sensemaking
    Algorithms & Theory Embeddings Neural Network Reinforcement Learning
    Apple researchers bring network science to UMAP, arguing that typical workflows focus only on its low-dimensional embedding. By analyzing UMAP's underlying kNN graph, the work aims to improve sensemaking and interpretation of dimensionality-reduction results.
    Read original (Apple Machine Learning Research) ↗
  • Simon Willison's Weblog · EN Developer Tools extract
    AI Worming through Word
    Prompt-injection 'worm' self-replicates through Microsoft Word's Copilot
    Microsoft
    Simon Willison highlights a prompt-injection variant by Håkon Måløy that upgrades attacks on Microsoft Word's Copilot into self-replicating worms. Hidden instructions in a source document can be interpreted by Copilot, which may both manipulate the drafted document and copy the instructions into the output, turning it into a new carrier that re-triggers in later Copilot workflows and propagates even without the attacker's original file present.
    Read original (Simon Willison's Weblog) ↗
  • Simon Willison's Weblog · EN Developer Tools extract
    Quoting Matthew Green
    Matthew Green on AI cryptanalysis arriving amid the post-quantum shift
    Algorithms & Theory Anthropic Claude Machine Learning Reinforcement Learning
    Simon Willison quotes cryptographer Matthew Green on the historic shift from EC/RSA public-key schemes to post-quantum algorithms such as HAWK. Green argues that if AI is going to become good at cryptanalysis, now, during this transition, is the ideal moment: in the best case it would build real confidence in the hard problems being standardized and make the cryptanalysis literature far more robust. This is commentary, not a claim of a specific break.
    Read original (Simon Willison's Weblog) ↗
  • arXiv cs.LG (Machine Learning) · EN Training & Fine-tuning
    Do You Really Need to Pretrain Q-Functions for Online RL Fine-Tuning?
    Fine-tuning Machine Learning Retrieval-Augmented Generation (RAG) Reinforcement Learning
    Read original (arXiv cs.LG (Machine Learning)) ↗
  • arXiv cs.CL (Computation and Language) · EN Developer Tools
    Mental World Modeling
    Neural Network Reinforcement Learning Software Engineering
    Read original (arXiv cs.CL (Computation and Language)) ↗
  • arXiv cs.LG (Machine Learning) · EN Developer Tools
    Inverse Learning of Latent Risk-Neutral Densities from Irregular Option Quotes
    Neural Network Transformer
    Read original (arXiv cs.LG (Machine Learning)) ↗
  • arXiv cs.CL (Computation and Language) · EN Developer Tools
    Pangram 4 Technical Report
    Reinforcement Learning
    Read original (arXiv cs.CL (Computation and Language)) ↗
  • arXiv cs.CL (Computation and Language) · EN Training & Fine-tuning
    DenseOn with the LateOn: Fully Open Dense and Late-Interaction Models for Multilingual, Long-Context, and Code Search
    Fine-tuning Machine Learning Retrieval-Augmented Generation (RAG)
    Read original (arXiv cs.CL (Computation and Language)) ↗
  • arXiv cs.CL (Computation and Language) · EN Developer Tools
    SpecFirst: Behavioral Specification Elicitation as a First-Class Step in Agent-Based Program Synthesis from Scratch
    AI Agents Neural Network Reinforcement Learning Software Engineering
    Read original (arXiv cs.CL (Computation and Language)) ↗
  • arXiv cs.AI (Artificial Intelligence) · EN New Model Releases
    OmegaUse-OfficeVal: Benchmarking LLM Agents on Long-Horizon Office-Suite Tasks with Economic Grounding
    AI Agents Inference Retrieval-Augmented Generation (RAG)
    Read original (arXiv cs.AI (Artificial Intelligence)) ↗
  • arXiv cs.CL (Computation and Language) · EN New Model Releases
    MindForge: Teaching Small Language Models Whole-Life-Cycle Software Engineering via Source-Free Program Synthesis
    AI Agents Fine-tuning Neural Network Retrieval-Augmented Generation (RAG) Software Engineering
    Read original (arXiv cs.CL (Computation and Language)) ↗