Search: “models”

Parameter Alignment Mitigates Catastrophic Forgetting in Multilingual Expert Language Models

arXiv:2606.00284v1 Announce Type: new Abstract: While continual pretraining~(CPT) is a practical way to extend large language models to new languages, naive finetuning on targeted data erodes existing

Research

Physical Object Understanding with a Physically Controllable World Model

DGX agent

arXiv:2606.00439v1 Announce Type: new Abstract: A central challenge in visual intelligence is learning the physical structure of scenes from raw videos: how regions form objects and the laws that gove

researcharxiv-cs-cv

2 Jun 2026

Position: Good Embodied Reward Models Need Bad Behavior Data

arXiv:2606.01036v1 Announce Type: new Abstract: This position paper argues that to obtain reliable embodied reward models, the community must invest in ``bad'' robot data: failed, suboptimal, error-pr

safetyarxiv-cs-ro

Local Ai

ProactiveLLM: Learning Active Interaction for Streaming Large Language Models

arXiv:2606.00523v1 Announce Type: new Abstract: Standard Large Language Models (LLMs) follow a read-then-generate paradigm, causing unnecessary latency and computation. Streaming LLMs alleviate this i

local-aiarxiv-cs-cl

Query-Limited Community Recovery in Stochastic Block Models

arXiv:2606.02055v1 Announce Type: cross Abstract: We study exact community recovery in the two-community stochastic block model on n vertices under limited and noisy access to network data. The learne

RealityTest: How People Probe AI Identity and Whether Models Disclose It

arXiv:2606.00168v1 Announce Type: new Abstract: AI systems are increasingly deployed in conversational settings where users may be uncertain whether they are speaking with a human or an AI. Despite mo

RefLoRA: Refactored Low-Rank Adaptation for Efficient Fine-Tuning of Large Models

arXiv:2505.18877v4 Announce Type: replace Abstract: Low-Rank Adaptation (LoRA) lowers the computational and memory overhead of fine-tuning large models by updating a low-dimensional subspace of the pr

Score-Control for Hallucination Reduction in Diffusion Models

model-releasesarxiv-cs-cv

arXiv:2606.00377v1 Announce Type: new Abstract: Diffusion models have emerged as the backbone of modern generative AI, powering advances in vision, language, audio and other modalities. Despite their

Strategizing at Speed: A Learned Model Predictive Game for Multi-Agent Drone Racing

model-releasesarxiv-cs-ro

arXiv:2602.06925v2 Announce Type: replace Abstract: Autonomous drone racing pushes the boundaries of high-speed motion planning and multi-agent strategic decision-making. Success in this domain requir

Task Structure Reverses Layerwise State Encoding in Sequence Models

arXiv:2606.00926v1 Announce Type: cross Abstract: Mechanistic studies of sequence models often treat layerwise state encodings as architectural traits: recurrent models concentrate readable state, att

researcharxiv-cs-cl

Tutorials

Towards a Physics Foundation Model

arXiv:2509.13805v4 Announce Type: replace-cross Abstract: Foundation models have revolutionized natural language processing through a ``train once, deploy anywhere'' paradigm, where a single pre-train

tutorialsarxiv-cs-ai

TrustLDM: Benchmarking Trustworthiness in Language Diffusion Models

arXiv:2606.00023v1 Announce Type: cross Abstract: The rapid development of Language Diffusion Models (LDMs) challenges the dominant position of auto-regressive competitors in language processing. Howe

WAON: A Large-Scale Japanese Image-Text Dataset for Cultural Adaptation in Contrastive Vision-Language Models

arXiv:2510.22276v3 Announce Type: replace-cross Abstract: Contrastive vision-language models have achieved remarkable progress through large-scale pretraining. Recent work has shown that removing Engl

When and How Much to Imagine: Adaptive Test-Time Scaling with World Models for Visual Spatial Reasoning

arXiv:2602.08236v2 Announce Type: replace-cross Abstract: Despite rapid progress in MLLMs, visual spatial reasoning remains unreliable when correct answers depend on how a scene would appear under uns

World Models for Robotic Manipulation: A Survey

arXiv:2606.00113v1 Announce Type: new Abstract: Robotic manipulation depends on the ability to anticipate how actions reshape objects, contacts, and scene geometry before execution. Learned world mode

safetyarxiv-cs-ro

X-Foresight: A Joint Vision-Action Causal Forecasting Network via Predictive World Modeling

arXiv:2605.24892v2 Announce Type: replace Abstract: Physical world knowledge resides mainly in videos. Equipping Vision-Language-Action (VLA) models with such knowledge is fundamental for safe and gen

safetyarxiv-cs-cv

BenHalluEval: A Multi-Task Hallucination Evaluation Framework for Large Language Models on Bengali

arXiv:2605.31483v1 Announce Type: new Abstract: Despite Bengali being the sixth most spoken language in the world, no prior work has systematically evaluated hallucination in large language models (LL

DeMaVLA: A Vision-Language-Action Foundation Model for Generalizable Deformable Manipulation

arXiv:2605.31286v1 Announce Type: cross Abstract: Real-world household robots require Vision-Language-Action (VLA) foundation models that can acquire reusable manipulation skills across diverse object

Emergent Languages in Populations of Language Model Agents: From Token Efficiency to Oversight Evasion

arXiv:2605.31170v1 Announce Type: cross Abstract: Monitoring autonomous language model agents currently relies mostly on surface behavior. But what happens when agent populations invent new languages

End-to-End Compression for Tabular Foundation Models

arXiv:2602.05649v2 Announce Type: replace Abstract: The long-standing dominance of gradient-boosted decision trees for tabular data has recently been challenged by in-context learning tabular foundati

Hardware

🆕Grok Imagine’s Video Agent Moment: Cosmos, xAI, World Models, Generative UI, & the Codex Phase for Video! https://www.latent.space/p/video…

🆕Grok Imagine’s Video Agent Moment: Cosmos, xAI, World Models, Generative UI, & the Codex Phase for Video! https://www.latent.space/p/video-agents @EthanHe_42, former @xai world model lead and @nvidia

hardwareswyx--x

Improving Small Language Models for Code Generation with Reinforcement Learning from Verification Feedback

arXiv:2605.30478v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) trains language models using programmatically checkable signals such as unit-test outcomes, enab

Motion Tracking with Muscles: Predictive Control of a Parametric Musculoskeletal Canine Model

arXiv:2506.23768v2 Announce Type: replace Abstract: We introduce a novel musculoskeletal model of a dog, procedurally generated from accurate 3D muscle meshes. Accompanying this model is a motion capt

researcharxiv-cs-ro

Local Ai

PatchWorld: Gradient-Free Optimization of Executable World Models

arXiv:2605.30880v1 Announce Type: cross Abstract: Text-agent environments are typically modeled as partially observable Markov decision processes (POMDPs), assuming that the simulator's latent state a

local-aiarxiv-cs-ai

The Flip Side of RLHF: On-Policy Feedback for Reward Model Self-Supervised Improvement

arXiv:2605.30888v1 Announce Type: new Abstract: Building strong reward models (RMs) for language model alignment is bottlenecked by the cost and difficulty of acquiring diverse and reliable preference

safetyarxiv-cs-cl

Experts say ChatGPT, Gemini, and other Western AI models are turbocharging Iran's cyber operations, helping it develop malware and launch phishing attacks (Jacob Judah/Financial Times)

Jacob Judah / Financial Times: Experts say ChatGPT, Gemini, and other Western AI models are turbocharging Iran's cyber operations, helping it develop malware and launch phishing attacks — Western AI m

model-releasestechmeme

31 May 2026

Alignment-Guided Score Matching for Text-to-Image Alignment in Diffusion Models

arXiv:2605.30038v1 Announce Type: cross Abstract: Diffusion models generate highly realistic images but often struggle with precise text-image alignment. While recent post-training methods improve ali

AMDP: Asynchronous Multi-Directional Pipeline Parallelism for Large-Scale Models Training

arXiv:2605.29664v1 Announce Type: cross Abstract: Pipeline parallelism is essential for large-scale model training, but existing asynchronous approaches often degrade convergence due to parameter mism

An End-to-End PyTorch Interface for Differentiable PDE Solvers: A RANS Model-Correction Study

arXiv:2605.28858v1 Announce Type: cross Abstract: This work presents an end-to-end strategy for solving inverse problems constrained by Partial Differential Equations within a fully differentiable Mac

Tutorials

BioArc: Discovering Optimal Neural Architectures for Biological Foundation Models

arXiv:2512.00283v3 Announce Type: replace-cross Abstract: Foundation models have revolutionized various fields such as natural language processing (NLP) and computer vision (CV). While efforts have be

tutorialsarxiv-cs-ai

Enhancing Membership Inference Attacks on Diffusion Models from a Frequency-Domain Perspective

arXiv:2505.20955v4 Announce Type: replace-cross Abstract: Diffusion models have achieved tremendous success in image generation, but they also raise significant concerns regarding privacy and copyrigh

researcharxiv-cs-lg

Entropy-KL Divergence-based Token Masking: A Novel Approach for Selective Fine-tuning of Large Language Models

arXiv:2605.29303v1 Announce Type: new Abstract: Supervised fine-tuning (SFT) followed by reinforcement learning (RL) has become a standard post-training paradigm for large language models. This paradi

safetyarxiv-cs-ai

Evaluating Dataset Watermarking for Fine-tuning Traceability of Customized Diffusion Models: A Comprehensive Benchmark and Removal Approach

arXiv:2511.19316v2 Announce Type: replace-cross Abstract: Recent fine-tuning techniques for diffusion models enable them to reproduce specific image sets, such as particular faces or artistic styles,

Evolutionary Rule Extraction from Corporate Default Prediction Models

arXiv:2605.29478v1 Announce Type: cross Abstract: Small and medium-sized enterprises (SMEs) represent the majority of firms in most economies and often face financial constraints and higher vulnerabil

Feature Geometry of LoRA Adapters: A Sparse Autoencoder Analysis of Representational Divergence in Fine-Tuned Language Models

arXiv:2605.28896v1 Announce Type: new Abstract: Low-Rank Adaptation (LoRA) has emerged as a widely adopted approach for adapting large language models, yet the internal representational changes induce

How's it going? Reinforcement learning in language models recruits a functional welfare axis

arXiv:2605.30232v1 Announce Type: cross Abstract: How does reinforcement learning shape a language model's internal representations? We present evidence that RL recruits a pre-existing representation

safetyarxiv-cs-cl

Is Your Diffusion Sampler Actually Correct? A Sampler-Centric Evaluation of Discrete Diffusion Language Models

arXiv:2602.19619v2 Announce Type: replace Abstract: Discrete diffusion language models (dLLMs) provide a fast and flexible alternative to autoregressive models (ARMs) via iterative denoising with para

researcharxiv-cs-lg

Large language models reorganize representational geometry during in-context learning

arXiv:2605.28854v1 Announce Type: new Abstract: Large language models (LLMs) exhibit remarkable flexibility: they can adapt to novel tasks from in-context examples without any parameter updates, a cap

Midpoint Generative Models

arXiv:2605.29920v1 Announce Type: new Abstract: We introduce Midpoint Generative Models (MGM), a principled framework for training one-step generative models. MGM is based on a simple symmetry of Flow

researcharxiv-cs-lg

Mind-Omni: A Unified Multi-Task Framework for Brain-Vision-Language Modeling via Discrete Diffusion

arXiv:2605.29591v1 Announce Type: new Abstract: Modeling the interplay between external stimuli and internal neural representations is a pivotal research area for Brain-Computer Interfaces (BCIs). A m

researcharxiv-cs-ai

Model Fusion via Retrofitting

arXiv:2507.00037v2 Announce Type: replace-cross Abstract: Model fusion seeks to combine independently trained neural networks into a single model without retraining, but is complicated by representati

safetyarxiv-cs-ai

Multi-Turn Adaptive Prompting Attack on Large Vision-Language Models

model-releasesarxiv-cs-cv

arXiv:2602.14399v2 Announce Type: replace Abstract: Multi-turn jailbreak attacks have proven effective against text-only large language models (LLMs), where malicious content is gradually introduced t

Pocket-Dentist: On-Device Dental Image Understanding via Efficient Multimodal Large Language Models

arXiv:2605.29299v1 Announce Type: cross Abstract: Evaluations of dental vision-language models remain fragmented across datasets, task definitions and metrics, and often ignore their computational cos

Prioritize the Process, Not Just the Outcome: Rewarding Latent Thought Trajectories Improves Reasoning in Looped Language Models

arXiv:2602.10520v3 Announce Type: replace Abstract: Looped Language Models (LoopLMs) perform multi-step latent reasoning prior to token generation and outperform conventional LLMs on reasoning benchma

Tutorials

Reasoning that Travels: Dissecting How Chain-of-Thought Transfers Across Models

arXiv:2605.28913v1 Announce Type: new Abstract: Large reasoning models (LRMs) often generate extensive chain-of-thought (CoT) traces before producing a final answer. As explicit textual artifacts, the

tutorialsarxiv-cs-cl

Spurious Prompts: Can Irrelevant Prompts Steer Large Language Models?

arXiv:2605.29678v1 Announce Type: new Abstract: Large language models are highly sensitive to prompts, but this sensitivity is usually studied through task-relevant instructions, demonstrations, or re

researcharxiv-cs-cl

Teaching Language Models to Check Grounded Claim Factuality with Human Test-Taking Strategies

arXiv:2605.29712v1 Announce Type: cross Abstract: Grounded claim factuality checking is important for large language model (LLM) applications such as retrieval-augmented generation, as it helps users

Three-dimensional Conditional Diffusion Models for Cosmological 21 cm Lightcone Emulation

arXiv:2605.29016v1 Announce Type: cross Abstract: We investigate conditional diffusion modeling for three-dimensional 21 cm lightcone emulation, focusing on cubes with a sky-plane size of 64imes64 and