model releases

Toward a Benchmark for Controllable Simulation of Imperfect Students with Large Language Models

arXiv:2605.25601v1 Announce Type: cross Abstract: Teacher education requires deliberate practice with learners who exhibit identifiable strengths, weaknesses, and partial mastery. Large language model

Model Releases

Towards Large Model Feature Coding

DGX agent

arXiv:2605.24025v1 Announce Type: cross Abstract: Large models have delivered remarkable performance across a wide range of perception and generation tasks, yet practical deployment is increasingly co

model-releasesarxiv-cs-lg

26 May 2026

TRACE: A taxonomy-grounded synthetic dataset for teaching-program generation and session interpretation in Applied Behavior Analysis

arXiv:2605.25038v1 Announce Type: new Abstract: Applied Behavior Analysis (ABA) is a clinical discipline whose documentation, teaching programs and multi-session behavioral logs, is formulaic and high

TRACER: A Semantic-Aware Framework for Fine-Grained Contamination Detection in Code LLMs

arXiv:2605.24079v1 Announce Type: cross Abstract: Data contamination is a known threat to the reliability of model evaluation. However, it remains underexplored in code large language models (LLMs), w

Trade-off Functions for DP-SGD with Subsampling based on Random Shuffling: Tight Upper and Lower Bounds

arXiv:2605.06259v2 Announce Type: replace Abstract: We derive a tight analysis of the trade-off function for Differentially Private Stochastic Gradient Descent (DP-SGD) with subsampling based on rando

TriVAL: A Tri-Validation Framework for Faithful Automatic Optimization Modeling

arXiv:2605.23966v1 Announce Type: cross Abstract: Optimization modeling serves as the pivotal bridge between natural-language problem descriptions and optimization solvers, and remains a cornerstone f

Trust but Verify: Prover-Verifier Deliberation for Selective LLM Prediction

arXiv:2605.25133v1 Announce Type: new Abstract: Reliably knowing when a language model is correct is almost as important as being correct. We introduce prover-verifier deliberation (PVD), an inference

Truthful Online Preference Aggregation for LLM Fine-Tuning in Mobile Crowdsourcing

arXiv:2605.24052v1 Announce Type: cross Abstract: To better serve users' demands in mobile applications (e.g., navigation), mobile crowdsourcing platforms can iteratively align large language model (L

TS-Skill: A Benchmark for Evaluating Analytical Skills in Time-Series Question Answering

arXiv:2605.24703v1 Announce Type: cross Abstract: Large language models (LLMs) and time-series language models (TSLMs) are increasingly applied to time-series question answering (TSQA). Unlike text-on

TTPrint: Evidence-Grounded TTP Extraction via Diverge-then-Converge Verification

arXiv:2605.25836v1 Announce Type: cross Abstract: Extracting MITRE ATT&CK techniques from cyber threat intelligence (CTI) reports is an open-set, multi-label problem requiring both high recall (not mi

TypedCSIP: Typed Counterfactual Pretraining for Chinese Legislative Conflict Classification

arXiv:2605.25474v1 Announce Type: new Abstract: TypedCSIP is a typed counterfactual pretraining method for the conflict-classification task of the LCR-CN benchmark (Zhao et al., 2026): given a (superi

Uber president says AI spending is getting ‘harder to justify’

model-releasesthe-verge-ai

After reportedly exhausting its annual AI budget just four months into 2026, Uber is now questioning whether it's actually seeing meaningful returns on its investments. In an interview with Rapid Resp

Uncertainty Decomposition via Cyclical SG-MCMC and Soft-label Learning for Subjective NLP

arXiv:2605.24773v1 Announce Type: new Abstract: Annotator disagreement in emotion classification reflects ambiguity intrinsic to emotion concepts and is essential for predictor-quality assessment in s

Understanding and Mitigating Premature Confidence for Better LLM Reasoning

arXiv:2605.24396v1 Announce Type: new Abstract: Long chains of thought (CoT) from current language models frequently contain logical gaps and unjustified leaps, limiting the gains from additional test

Understanding Conversational Patterns in Multi-agent Programming: A Case Study on Fibonacci Game Development

arXiv:2605.24138v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly applied to software engineering (SE), yet their potential for autonomous, role-oriented collaboration re

Uni-DPO: A Unified Paradigm for Dynamic Preference Optimization of LLMs

arXiv:2506.10054v4 Announce Type: replace-cross Abstract: Direct Preference Optimization (DPO) has emerged as a cornerstone of reinforcement learning from human feedback (RLHF) due to its simplicity a

URS: A Unified Neural Routing Solver for Cross-Problem Zero-Shot Generalization

arXiv:2509.23413v2 Announce Type: replace Abstract: Multi-task neural routing solvers have emerged as a promising paradigm for their ability to solve multiple vehicle routing problems (VRPs) using a s

UtilityMax Prompting: A Formal Framework for Multi-Objective Large Language Model Tasks

arXiv:2603.11583v4 Announce Type: replace-cross Abstract: The success of a Large Language Model (LLM) task depends heavily on its prompt. Most use-cases specify prompts using natural language, which i

UWM-JEPA: Predictive World Models That Imagine in Belief Space

arXiv:2605.25313v1 Announce Type: cross Abstract: World models for partially observed environments must imagine multiple compatible hidden futures and steer between them under counterfactual actions.

v0.13.0 of Exo just dropped, and it's one I've been looking forward to for a while. tl;dr swapping out anthropic for @ollama cloud dropped m…

v0.13.0 of Exo just dropped, and it's one I've been looking forward to for a while. tl;dr swapping out anthropic for @ollama cloud dropped my usage costs from 30/day to just 20 per MONTH with no notic

model-releasesollama--x

v0.30.0-rc26: Merge remote-tracking branch 'upstream/main' into llama-runner-phase-0

model-releasesollama-releases

This release candidate merges updates from the upstream main branch into the llama-runner-phase-0 branch, likely incorporating recent improvements and bug fixes into the development version. Version 0

V3H: View Variation and View Heredity for Incomplete Multi-view Clustering

arXiv:2011.11194v4 Announce Type: replace Abstract: Real data often appear in the form of multiple incomplete views. Incomplete multi-view clustering is an effective method to integrate these incomple

VaaWIT: Visual-Aware Adaptation of Large Language Models for Multilingual Web Image Translation

arXiv:2605.24675v1 Announce Type: cross Abstract: Translating text embedded in Web images is crucial for improving content accessibility and cross-lingual information retrieval, particularly within so

vAttention: Verified Sparse Attention

arXiv:2510.05688v2 Announce Type: replace-cross Abstract: State-of-the-art sparse attention methods for reducing decoding latency fall into two main categories: approximate top-k (and its extension, t

VeriTrace: Evolving Mental Models for Deep Research Agents

arXiv:2605.26081v1 Announce Type: new Abstract: Deep research agents face vast, interdependent, and pervasively uncertain information. Existing systems explore what evolving intermediate representatio

ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks

arXiv:2605.25388v1 Announce Type: new Abstract: Nucleotide sequences constitute the fundamental genetic basis of biological systems, rendering viral genomic analysis critical for biomedical advancemen

Visual-Redundancy-Controlled Parallel Decoding for Diffusion-Based Multimodal Large Language Models

arXiv:2605.25820v1 Announce Type: new Abstract: Diffusion-based multimodal large language models (dMLLMs) decode by iteratively predicting tokens at multiple masked positions in parallel. This turns e

VisualOverload: Probing Visual Understanding of VLMs in Really Dense Scenes

arXiv:2509.25339v3 Announce Type: replace-cross Abstract: Is basic visual understanding really solved in state-of-the-art VLMs? We present VisualOverload, a slightly different visual question answerin

We have, as far as I can tell, no good tests of the productivity impact of the autonomous coding tools that appeared starting in December 20…

model-releasesethan-mollick--x

We have, as far as I can tell, no good tests of the productivity impact of the autonomous coding tools that appeared starting in December 2025. Every paper out there is from prior to the Claude Code/C

We’ve shipped a security-guidance plugin for Claude Code that helps identify and fix vulnerabilities as you’re writing code. Available for a…

model-releasesboris-cherny--x

We’ve shipped a security-guidance plugin for Claude Code that helps identify and fix vulnerabilities as you’re writing code. Available for all Claude Code users. Install from the plugin marketplace (/

What Makes a Medical Checker Trainable? Diagnosing Signal Collapse and Reward Hacking in Checker-Guided RAG for Biomedical QA

arXiv:2605.25988v1 Announce Type: new Abstract: Medical RAG needs evidence-grounded claims, so plugging a claim-level NLI checker into retrieval-augmented RL is intuitive. extbf{We find that the check

When Can We Trust Early Warnings? Leakage-Excluded Early Outcome Prediction from LMS Interaction Logs

arXiv:2605.25794v1 Announce Type: new Abstract: Early-warning models built from Learning Management System (LMS) logs aim to predict end-of-course outcomes early enough to enable timely learner suppor

When Correct Beliefs Collapse: Epistemic Resilience of LLMs under Clinical Pressure

arXiv:2605.23932v1 Announce Type: new Abstract: Despite strong medical benchmark accuracy, LLMs can exhibit severe multi-turn sycophancy in clinical dialogue, abandoning initial correct diagnosis unde

When Do LLM Agents Treat Surface Noise Differently from Semantic Noise? A 68-Cell Measurement Study with a Held-Out Trace-Level Validation

arXiv:2605.25981v1 Announce Type: new Abstract: We document an empirical phenomenon in chain-of-thought and ReAct agents driven by ten large language models from seven architecture families: meaning-b

When Mean CE Fails: Median CE Can Better Track Language Model Quality

arXiv:2605.24667v1 Announce Type: new Abstract: Mean cross-entropy is the standard validation metric for language models, but it can fail to track model quality during training. We examine this in two

When Reasoning Hurts: Source-Aware Evaluation of Frontier LLMs for Clinical SOAP Note Generation

arXiv:2605.24902v1 Announce Type: cross Abstract: Reasoning-enabled LLMs perform strongly on medical reasoning benchmarks, but it remains unclear whether these gains transfer to structured clinical do

When Search Becomes Memory: Turning Robot Design Trials into Transferable Skills

arXiv:2605.25832v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used as proposal generators for evolutionary robot design, yet most loops remain memoryless: simulator r

When the Manual Lies: A Realistic Benchmark to Evaluate MCP Poisoning Attacks for LLM Agents

arXiv:2605.24069v1 Announce Type: cross Abstract: The rise of tool-using Large Language Model (LLM) agents, standardized by protocols like the Model Context Protocol (MCP), has unlocked unprecedented

WhenLoss: Diagnosing Write and Retrieval Bottlenecks in Long-Context Memory Systems

arXiv:2605.24579v1 Announce Type: new Abstract: Long-context memory systems often fail under fixed budgets, but end-to-end evaluation does not reveal whether evidence was discarded during compression

Who judges the judges? Governance from metrics: a runtime framework for continuous LLM compliance monitoring

arXiv:2605.24737v1 Announce Type: cross Abstract: Current approaches to AI compliance treat conformity as a binary, audit-time verdict rather than a continuous, measurable property of production syste

WhoSaidIt: Human-LLM Collaborative Annotation for Text-Based Multilingual Speaker-Attribute Classification

arXiv:2605.26070v1 Announce Type: new Abstract: Annotating speaker attributes from text is inherently ambiguous, particularly in multilingual settings where demographic and social cues are implicit an

Whose Alignment? Comparing LLM Process Alignment Across Diverse Organizational Decision Contexts

arXiv:2605.25256v1 Announce Type: new Abstract: Aligning AI systems with organizational decision-making is typically framed as a single-target problem: make the model behave like the organization. We

WideDepth: Millimeter-Accurate Benchmark for Fisheye Depth Estimation

model-releasesarxiv-cs-ro

arXiv:2605.24074v1 Announce Type: cross Abstract: Fisheye cameras are increasingly adopted in robotics for near-field manipulation, navigation, and immersive perception, yet indoor depth benchmarks wi

WLNO: Wavelet-Laplace Neural Operator for Solving Partial Differential Equations

arXiv:2605.24658v1 Announce Type: new Abstract: This work introduces the Wavelet-Laplace Neural Operator (WLNO), a novel neural operator that fuses Haar wavelet multi-scale spatial decomposition with

World-State Transformations for Neuro-symbolic Interactive Storytelling

arXiv:2605.24719v1 Announce Type: cross Abstract: Large Language Models (LLMs) have changed the possibilities of Interactive Storytelling systems that process free-text user input. However, as more of

WorldGUI: An Interactive Benchmark for Desktop GUI Automation from Any Starting Point

arXiv:2502.08047v5 Announce Type: replace Abstract: Recent progress in GUI agents has substantially improved visual grounding, yet robust planning remains challenging, particularly when the environmen

A Comparative Evaluation of Structural Topic Models and BERTopic for Short, Open-Ended Survey Responses

arXiv:2605.23093v1 Announce Type: new Abstract: Topic modeling in applied psychology increasingly spans two methodological traditions: probabilistic bag-of-words models and newer embedding-based appro

25 May 2026

A European Multi-Center Breast Cancer MRI Dataset