Search: “model-releases”

Decoupled Training with Local Reinforcement Fine-Tuning in Federated Learning

arXiv:2605.27900v1 Announce Type: new Abstract: Federated Learning (FL) with pre-trained Vision-Language Models (VLMs) has emerged as a promising paradigm for various downstream tasks. By leveraging i

Model Releases

Deepfake-Eval-2024: A Multi-Modal In-the-Wild Benchmark of Deepfakes Circulated in 2024

DGX agent

arXiv:2503.02857v5 Announce Type: replace-cross Abstract: In the age of increasingly realistic generative AI, robust deepfake detection is essential for mitigating fraud and disinformation. While many

model-releasesarxiv-cs-ai

28 May 2026

DeepSciVerify: Verifying Scientific Claim--Citation Alignment via LLM-Driven Evidence Escalation

arXiv:2605.27710v1 Announce Type: new Abstract: Misalignment between claims and their cited evidence is a common failure mode in reports generated by large language models, limiting their reliability

Deformable Gaussian Occupancy: Decoupling Rigid and Nonrigid Motion with Factorized Distillation

arXiv:2605.28587v1 Announce Type: new Abstract: Understanding dynamic 3D environments is essential for safe autonomous driving, particularly when reasoning about human-centric, nonrigid agents. Howeve

DEPART: DEcomposing PARiTy across Multilingual LLMs

arXiv:2605.28163v1 Announce Type: cross Abstract: Multilingual Large Language Models (mLLMs) leaderboards report per-language accuracy but rarely explain why disparities emerge, leaving systemic biase

Detection Without Correction: A Two-Parameter Decomposition of Multi-Stage LLM Pipelines

arXiv:2605.27559v1 Announce Type: cross Abstract: Multi-stage LLM pipelines that perform multi-agent debate, intrinsic self-correction, or retrieval-augmented verification exhibit puzzling aggregate b

'Developers can update Claude’s instructions mid-task without breaking the prompt cache or routing the update through a user turn' wtf? how?…

'Developers can update Claude’s instructions mid-task without breaking the prompt cache or routing the update through a user turn' wtf? how?? Introducing Claude Opus 4.8: it builds on Opus 4.7 with sh

model-releasesswyx--x

Did this actually happen? It seems very suspicious.

model-releasesethan-mollick--x

Did this actually happen? It seems very suspicious. 'An AI consultant tells Axios one of their clients recently spent half a billion dollars in a single month after failing to put usage limits on Clau

Differential syntactic and semantic encoding in LLMs

arXiv:2601.04765v4 Announce Type: replace-cross Abstract: We study how syntactic and semantic information is encoded in inner layer representations of Large Language Models (LLMs), focusing on the ver

Diffusion-Based Ukrainian Handwritten Text Generation with Cross-Domain Style Transfer

arXiv:2605.27487v1 Announce Type: cross Abstract: Handwritten text generation (HTG) conditioned on writer style has been widely studied for Latin scripts, but remains underexplored for low-resource an

Dimensionality Reduction for Robust Federated Learning: A Theoretical Analysis and Convergence Guarantee

arXiv:2605.28335v1 Announce Type: new Abstract: Federated Learning (FL) enables multiple clients to collaboratively train models without sharing raw data, but it is highly vulnerable to Byzantine atta

DisasterBench: Benchmarking LLM Planning under Typed Tool Interface Constraints

arXiv:2605.27957v1 Announce Type: new Abstract: Disasters cause severe societal impacts, demanding rapid coordination of heterogeneous AI tools, from satellite analysis to flood prediction and damage

Disentangling Language Roles in Multilingual LLM Task Execution

arXiv:2605.27649v1 Announce Type: new Abstract: Multilingual LLMs are increasingly used when instruction, source content, and required response languages do not coincide. Existing benchmarks have expa

Do Agents Think Deeper? A Mechanistic Investigation of Layer-Wise Dynamics in Sequential Planning

arXiv:2605.27935v1 Announce Type: new Abstract: Recent mechanistic studies suggest that large language models (LLMs) may utilize their depth inefficiently in standard single-turn tasks. Whether this s

Do Audio LLMs Listen or Read? Analyzing and Mitigating Paralinguistic Failures with VoxParadox

arXiv:2605.27772v1 Announce Type: cross Abstract: Audio large language models (Audio LLMs) demonstrate strong performance on speech understanding tasks, yet their ability to understand paralinguistic

Do Clinical Models Change Treatment Decisions?

arXiv:2605.28129v1 Announce Type: new Abstract: Clinical foundation models are evaluated with factual or exam-style medical QA, but treatment decisions must change when patient context changes. We int

Do LLMs Build World Models From Text? A Multilingual Diagnostic of Spatial Reasoning

arXiv:2605.28277v1 Announce Type: new Abstract: Whether large language models (LLMs) construct internal spatial world models from pure-text descriptions remains contested, and whether such capabilitie

Do LLMs Favor Their Providers? Measuring Vertical Integration Bias in Code Generation

arXiv:2605.28515v1 Announce Type: cross Abstract: Large Language Models (LLMs) have become an integral part of software development, especially with the advent of agentic capabilities. Yet, many front

Do Models Know Why They Changed Their Mind? Interpretability and Faithfulness of Chain-of-Thought Under Knowledge Conflict

arXiv:2605.27773v1 Announce Type: cross Abstract: When a language model sees a document contradicting its training knowledge, it must choose: follow the document or trust itself. Prior work proved thi

Do We Really Need Quantum Machine Learning?: A Multidimensional Empirical Study

arXiv:2605.27923v1 Announce Type: cross Abstract: The rapid growth of computer vision and increasingly complex image recognition tasks has exposed fundamental computational limitations of classical ma

Dr-CiK: A Testbed for Foresight-Driven Agents

arXiv:2605.27904v1 Announce Type: new Abstract: Time series forecasting in real-world settings often depends not only on historical observations, but also on external context that must be actively dis

DriveWAM: Video Generative Priors Enable Scalable World-Action Modeling for Autonomous Driving

arXiv:2605.28544v1 Announce Type: new Abstract: Pretrained foundation models have become an important basis for end-to-end autonomous driving. In contrast to vision-language models pretrained primaril

DRTriton: Large-Scale Synthetic Data Driven Reinforcement Learning for Triton Kernel Generation

arXiv:2603.21465v2 Announce Type: replace Abstract: Developing efficient CUDA kernels is a fundamental yet challenging task in the generative AI industry. Recent research leverages Large Language Mode

DynaSchedBench: Calibrated Dynamic Scheduling Benchmarks and Observability Paradox in LLM-based Scheduling Agents

arXiv:2605.27566v1 Announce Type: new Abstract: Progress in neural combinatorial optimization for Dynamic Flexible Job Shop Scheduling Problem (DFJSP) is currently hindered by a methodological tension

Efficient and Scalable Provenance Tracking for LLM-Generated Code Snippets

arXiv:2605.28510v1 Announce Type: cross Abstract: Large language models (LLMs) for code completion and generation are increasingly used in software development, yet they may reproduce training example

Efficient Pre-Training of LLMs through Truncated SVD Layers

arXiv:2605.28573v1 Announce Type: cross Abstract: The massive scaling of Large Language Models (LLMs) has made pretraining increasingly cost-prohibitive. While low-rank representation and orthonormal

EgoBench: An Interactive Egocentric Multimodal Benchmark for Tool-Using Agents

arXiv:2605.27820v1 Announce Type: new Abstract: As AI agents increasingly operate in open, real-world environments, they require a deep synergy of multimodal perception, tool invocation with multi-hop

Energy-Structured Low-Rank Adaptation for Continual Learning

arXiv:2605.27482v1 Announce Type: cross Abstract: While orthogonal subspace methods try to mitigate task interference in Continual Learning (CL), they often suffer from energy diffusion across the bas

Enhancing Trustworthy GUI Grounding via Self-Critiqued Reinforcement Learning

arXiv:2510.27266v2 Announce Type: replace Abstract: Autonomous graphical user interface (GUI) agents rely on accurate GUI grounding, which maps language instructions to on-screen coordinates, to execu

ESC-Skills: Discovering and Self-Evolving Skills for Emotional Support Conversations

arXiv:2605.27908v1 Announce Type: cross Abstract: Existing emotional support conversation (ESC) systems mainly rely on end-to-end response generation or coarse strategy supervision, offering limited i

EVADE-Bench: Multimodal Benchmark for Evaluating and Enhancing Evasive Content Detection

arXiv:2505.17654v4 Announce Type: replace-cross Abstract: E-commerce platforms increasingly rely on Large Language Models (LLMs) and Vision Language Models (VLMs) to detect illicit or misleading produ

Evaluating Local Explainability Metrics for Machine Learning Models on Tabular Data

arXiv:2605.27618v1 Announce Type: new Abstract: Despite the wide use of explainability techniques to attempt to understand the behavior of Artificial Intelligence (AI), the generated explanations may

EventShiftFlow: Towards Hardware-efficient FPGA-based Flow Estimation

arXiv:2605.28312v1 Announce Type: cross Abstract: Event-based vision sensors offer asynchronous, high-temporal-resolution measurements that are attractive for low-latency robotic perception, but many

Every9D-21M: Large-Scale Real-World 9D Canonicalization of Everyday Objects

arXiv:2605.28270v1 Announce Type: new Abstract: Estimating the 9D pose of everyday objects from a single real-world image remains challenging. This is largely due to the lack of large-scale supervisio

Evolving Dataflow to process massive datasets for machine learning

model-releasesgoogle-cloud-ai

Google created MapReduce more than 20 years ago to solve the scaling problems in data processing that the then young company was running into. The AI era that we are in now demands efficient, large-sc

EvoSpec: Evolving Speculative Decoding via Real-Time Vocabulary and Parameter AdaptationTarget

arXiv:2605.27390v1 Announce Type: cross Abstract: Speculative decoding accelerates Large Language Model inference via a draft-then-verify paradigm, yet the output projection layer becomes a bottleneck

Exploratory Experience Shapes the Geometry of Predictive Representations

arXiv:2605.27929v1 Announce Type: cross Abstract: Active sensing links behavior and learning through an action-perception loop: actions determine the observations used to update internal predictive mo

FactReview: Evidence-Grounded Peer Review with Execution-Based Claim Verification

arXiv:2604.04074v3 Announce Type: replace Abstract: LLM-based reviewing systems typically take only the manuscript as input, leaving literature and code-based claims hard to verify. We present FactRev

Federated Learning for Multivariate Time Series Anomaly Detection in Industrial Automation

arXiv:2605.27486v1 Announce Type: new Abstract: Federated learning (FL) has broadened the horizon for multivariate time series anomaly detection (MTSAD). However, benchmarking such anomaly detection m

FedMPT: Federated Multi-label Prompt Tuning of Vision-Language Models

arXiv:2605.28347v1 Announce Type: new Abstract: Multi-Label Recognition (MLR) based on Vision-Language Models (VLMs) aims to leverage their pre-trained knowledge to better adapt complex recognition sc

Finding Miscompiles for Fun, Not Profit

model-releasessemianalysis

This article likely discusses the discovery and analysis of compiler bugs or miscompilation errors in software development tools, exploring how developers identify these issues and their implications

Finding Miscompiles for Fun, Not Profit Or: You don’t need access to Claude Mythos to spend $10,000 in an afternoon https://newsletter.semia…

model-releasesdylan-patel--x

This post discusses how compiler bugs or miscompiles can be discovered and exploited without expensive AI systems, illustrating that significant computational costs can be incurred quickly when identi

FLORO: A Multimodal Geospatial Foundation Model for Ecological Remote Sensing Across Sensors and Scales

arXiv:2605.28174v1 Announce Type: cross Abstract: Foundation models offer a promising route to transferable remote sensing representations, but many current approaches depend on very large pretraining

ForestHG-Trace: Traceable Long-Horizon Ecological Reasoning over Large-Scale Forest Scenes

arXiv:2605.27590v1 Announce Type: new Abstract: Remote sensing question answering (RS-QA) often requires more than direct semantic prediction, especially in large-scale forest scenes where ecological

FPMoE: A Sparse Mixture-of-Experts Approach to Functional Code Generation

arXiv:2605.27849v1 Announce Type: cross Abstract: Despite rapid progress in LLM-based code generation, existing models are predominantly trained on imperative languages, leaving functional programming

Framing Matters: Addressing Framing Sensitivity in Decision-Making through Behaviorally-Grounded Value Alignment

arXiv:2605.28188v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly deployed in high-stakes decision-making settings such as legal reasoning, where consistency under factuall

From Detection to Mechanism: Cross-Attention Graph Neural Networks Enable Drug-Drug Interaction Type Prediction An Ablation Study with Acetylsalicylic Acid Validation

arXiv:2605.27861v1 Announce Type: cross Abstract: Predicting whether two drugs interact (binary detection) is a substantially dif- ferent task from predicting the mechanism type of that interaction (m

From Fact Overwriting to Knowledge Evolution: Causal Editing via On-Policy Self-Distillation

arXiv:2605.28303v1 Announce Type: new Abstract: While Knowledge Editing (KE) enables efficient updates, its dominant Static Fact Overwriting paradigm treats LLMs as discrete databases, forcibly inject