Search: “models”

Towards Streaming Target Speaker Extraction via Chunk-wise Interleaved Splicing of Autoregressive Language Model

arXiv:2604.19635v1 Announce Type: cross Abstract: While generative models have set new benchmarks for Target Speaker Extraction (TSE), their inherent reliance on global context precludes deployment in

researcharxiv-cs-ai

22 Apr 2026

Safety

User Simulation in the Era of Generative AI: User Modeling, Synthetic Data Generation, and System Evaluation

DGX agent

arXiv:2501.04410v2 Announce Type: replace Abstract: User simulation is an emerging interdisciplinary topic with multiple critical applications in the era of Generative AI. It involves creating an inte

safetyarxiv-cs-ai

22 Apr 2026

Watch the Weights: Unsupervised monitoring and control of fine-tuned LLMs

arXiv:2508.00161v3 Announce Type: replace-cross Abstract: The releases of powerful open-weight large language models (LLMs) are often not accompanied by access to their full training data. Existing in

22 Apr 2026

Attraction, Repulsion, and Friction: Introducing DMF, a Friction-Augmented Drifting Model

arXiv:2604.18194v1 Announce Type: cross Abstract: Drifting Models [Deng et al., 2026] train a one-step generator by evolving samples under a kernel-based drift field, avoiding ODE integration at infer

local-aiarxiv-cs-cv

DeInfer: Efficient Parallel Inferencing for Decomposed Large Language Models

arXiv:2604.17709v1 Announce Type: new Abstract: Existing works on large language model (LLM) decomposition mainly focus on improving performance on downstream tasks, but they ignore the poor parallel

Depth Adaptive Efficient Visual Autoregressive Modeling

arXiv:2604.17286v1 Announce Type: new Abstract: Visual Autoregressive (VAR) modeling inefficiently applies a fixed computational depth to each position when generating high-resolution images. While ex

Different Paths to Harmful Compliance: Behavioral Side Effects and Mechanistic Divergence Across LLM Jailbreaks

arXiv:2604.18510v1 Announce Type: cross Abstract: Open-weight language models can be rendered unsafe through several distinct interventions, but the resulting models may differ substantially in capabi

local-aiarxiv-cs-cl

EvoComp: Learning Visual Token Compression for Multimodal Large Language Models via Semantic-Guided Evolutionary Labeling

arXiv:2604.17087v1 Announce Type: new Abstract: Recent Multimodal Large Language Models (MLLMs) have demonstrated strong performance on vision-language understanding tasks, yet their inference efficie

GoCoMA: Hyperbolic Multimodal Representation Fusion for Large Language Model-Generated Code Attribution

arXiv:2604.16377v1 Announce Type: new Abstract: Large Language Models (LLMs) trained on massive code corpora are now increasingly capable of generating code that is hard to distinguish from human-writ

HPLT 3.0: Very Large-Scale Multilingual Resources for LLMs and MT. Mono- and Bi-lingual Data, Multilingual Evaluation, and Pre-Trained Models

arXiv:2511.01066v3 Announce Type: replace Abstract: We present an ongoing initiative to provide open, very large, high-quality, and richly annotated textual datasets for almost 200 languages. At 30 tr

Improving Radio Interferometry Imaging by Explicitly Modeling Cross-Domain Consistency in Reconstruction

arXiv:2604.16794v1 Announce Type: new Abstract: Radio astronomy plays a crucial role in understanding the universe, particularly within the realm of non-thermal astrophysics. Images of celestial objec

Instinct vs. Reflection: Unifying Token and Verbalized Confidence in Multimodal Large Models

arXiv:2604.17274v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have demonstrated exceptional capabilities in various perception and reasoning tasks. Despite this success, ens

safetyarxiv-cs-cv

Jailbreaking Large Language Models with Morality Attacks

arXiv:2604.17053v1 Announce Type: new Abstract: Pluralism alignment with AI has the sophisticated and necessary goal of creating AI that can coexist with and serve morally multifaceted humanity. Resea

safetyarxiv-cs-cl

Latent-Compressed Variational Autoencoder for Video Diffusion Models

arXiv:2604.16479v1 Announce Type: new Abstract: Video variational autoencoders (VAEs) used in latent diffusion models typically require a sufficiently large number of latent channels to ensure high-qu

Linking Exteroception and Proprioception through Improved Contact Modeling for Soft Growing Robots

arXiv:2507.10694v2 Announce Type: replace Abstract: Passive deformation due to compliance is a commonly used benefit of soft robots, providing opportunities to achieve robust actuation with few active

researcharxiv-cs-ro

Method for Aggregating Unstructured Data Using Large Language Models

model-releasesarxiv-cs-lg

arXiv:2604.16425v1 Announce Type: cross Abstract: This paper presents a method for the automated collection and aggregation of unstructured data from diverse web sources, utilizing Large Language Mode

Model in Distress: Sentiment Analysis on French Synthetic Social Media

arXiv:2604.18226v1 Announce Type: new Abstract: Automated analysis of customer feedback on social media is hindered by three challenges: the high cost of annotated training data, the scarcity of evalu

Predictive Modeling of Natural Medicinal Compounds for Alzheimer Disease Using Cheminformatics

arXiv:2604.18316v1 Announce Type: cross Abstract: The most common cause of dementia is Alzheimer disease, a progressive neurodegenerative disorder affecting older adults that gradually impairs memory,

researcharxiv-cs-lg

Reasoning on the Manifold: Bidirectional Consistency for Self-Verification in Diffusion Language Models

arXiv:2604.16565v1 Announce Type: new Abstract: While Diffusion Large Language Models (dLLMs) offer structural advantages for global planning, efficiently verifying that they arrive at correct answers

safetyarxiv-cs-lg

Rethinking Jailbreak Detection of Large Vision Language Models with Representational Contrastive Scoring

arXiv:2512.12069v3 Announce Type: replace-cross Abstract: Large Vision-Language Models (LVLMs) are vulnerable to a growing array of multimodal jailbreak attacks, necessitating defenses that are both g

safetyarxiv-cs-cl

Agents

SERM: Self-Evolving Relevance Model with Agent-Driven Learning from Massive Query Streams

arXiv:2601.09515v2 Announce Type: replace Abstract: Due to the dynamically evolving nature of real-world query streams, relevance models struggle to generalize to practical search scenarios. A sophist

agentsarxiv-cs-cl

Industry

Source: a handful of unauthorized users in a private Discord channel have been accessing Anthropic's Mythos model since the day the company announced it (Rachel Metz/Bloomberg)

Rachel Metz / Bloomberg: Source: a handful of unauthorized users in a private Discord channel have been accessing Anthropic's Mythos model since the day the company announced it — A small group of una

industrytechmeme

SPaRSe-TIME: Saliency-Projected Low-Rank Temporal Modeling for Efficient and Interpretable Time Series Prediction

arXiv:2604.17350v1 Announce Type: cross Abstract: Time series forecasting is traditionally dominated by sequence-based architectures such as recurrent neural networks and attention mechanisms, which p

applicationsarxiv-cs-lg

SpidR-Adapt: A Universal Speech Representation Model for Few-Shot Adaptation

arXiv:2512.21204v2 Announce Type: replace Abstract: Human infants, with only a few hundred hours of speech exposure, acquire basic units of new languages, highlighting a striking efficiency gap compar

The Gait Signature of Frailty: Transfer Learning based Deep Gait Models for Scalable Frailty Assessment

arXiv:2603.24434v2 Announce Type: replace Abstract: Frailty is a condition in aging medicine characterized by diminished physiological reserve and increased vulnerability to stressors. However, frailt

TokenChain: A Discrete Speech Chain via Semantic Token Modeling

arXiv:2510.06201v1 Announce Type: cross Abstract: Machine Speech Chain, simulating the human perception-production loop, proves effective in jointly improving ASR and TTS. We propose TokenChain, a ful

applicationsarxiv-cs-lg

VocabTailor: Dynamic Vocabulary Selection for Downstream Tasks in Small Language Models

arXiv:2508.15229v3 Announce Type: replace Abstract: Small Language Models (SLMs) provide computational advantages in resource-constrained environments, yet memory limitations remain a critical bottlen

local-aiarxiv-cs-cl

Where's the raccoon with the ham radio? (ChatGPT Images 2.0)

model-releasessimon-willison

OpenAI released ChatGPT Images 2.0 today, their latest image generation model. On the livestream Sam Altman said that the leap from gpt-image-1 to gpt-image-2 was equivalent to jumping from GPT-3 to G

A useful ward against slop story/science posts on X is noting which is in the character limit. All of the models struggle to do 280 characte…

applicationsethan-mollick--x

A useful ward against slop story/science posts on X is noting which is in the character limit. All of the models struggle to do 280 character summaries on their first pass, and most of the people crea

Anthropomorphism and Trust in Human-Large Language Model interactions

arXiv:2604.15316v1 Announce Type: cross Abstract: With large language models (LLMs) becoming increasingly prevalent in daily life, so too has the tendency to attribute to them human-like minds and emo

researcharxiv-cs-ai

Beyond Single-Model Optimization: Preserving Plasticity in Continual Reinforcement Learning

arXiv:2604.15414v1 Announce Type: cross Abstract: Continual reinforcement learning must balance retention with adaptation, yet many methods still rely on single-model preservation, committing to one e

local-aiarxiv-cs-ai

CiPO: Counterfactual Unlearning for Large Reasoning Models through Iterative Preference Optimization

arXiv:2604.15847v1 Announce Type: new Abstract: Machine unlearning has gained increasing attention in recent years, as a promising technique to selectively remove unwanted privacy or copyrighted infor

Convolutionally Low-Rank Models with Modified Quantile Regression for Interval Time Series Forecasting

arXiv:2604.15791v1 Announce Type: new Abstract: The quantification of uncertainty in prediction models is crucial for reliable decision-making, yet remains a significant challenge. Interval time serie

applicationsarxiv-cs-lg

Industry

Dataset 2: Drift, named after Drift Diffusion Modeling. https://huggingface.co/datasets/DJLougen/drift-preview-5k This is a bit of different…

Dataset 2 (Drift) is a 5,000-sample preview dataset hosted on Hugging Face, named after drift diffusion modeling concepts. The dataset appears to represent a novel or experimental approach to data col

industryclem-delangue--x

Information-Consistent Language Model Recommendations through Group Relative Policy Optimization

arXiv:2512.12858v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are increasingly deployed in business-critical domains such as finance, education, healthcare, and customer suppo

safetyarxiv-cs-ai

Online Distributionally Robust LLM Alignment via Regression to Relative Reward

model-releasesarxiv-cs-lg

arXiv:2509.19104v2 Announce Type: replace Abstract: Reinforcement Learning with Human Feedback (RLHF) has become crucial for aligning Large Language Models (LLMs) with human intent. However, existing

SwanNLP at SemEval-2026 Task 5: An LLM-based Framework for Plausibility Scoring in Narrative Word Sense Disambiguation

arXiv:2604.16262v1 Announce Type: new Abstract: Recent advances in language models have substantially improved Natural Language Understanding (NLU). Although widely used benchmarks suggest that Large

Give your local Ollama models a personal knowledge bank (graph-based, not just vector search)

This post discusses Graph RAG, an approach that uses local LLMs with Ollama to build graph-based knowledge indexes from source documents by deriving entity knowledge graphs and pregenerating community

local-air-ollama

19 Apr 2026

Acceptance Dynamics Across Cognitive Domains in Speculative Decoding

arXiv:2604.14682v1 Announce Type: cross Abstract: Speculative decoding accelerates large language model (LLM) inference. It uses a small draft model to propose a tree of future tokens. A larger target

AD4AD: Benchmarking Visual Anomaly Detection Models for Safer Autonomous Driving

model-releasesarxiv-cs-cv

arXiv:2604.15291v1 Announce Type: new Abstract: The reliability of a machine vision system for autonomous driving depends heavily on its training data distribution. When a vehicle encounters significa

Assessing the Potential of Masked Autoencoder Foundation Models in Predicting Downhole Metrics from Surface Drilling Data

arXiv:2604.15169v1 Announce Type: new Abstract: Oil and gas drilling operations generate extensive time-series data from surface sensors, yet accurate real-time prediction of critical downhole metrics

researcharxiv-cs-lg

CURA: Clinical Uncertainty Risk Alignment for Language Model-Based Risk Prediction

arXiv:2604.14651v1 Announce Type: new Abstract: Clinical language models (LMs) are increasingly applied to support clinical risk prediction from free-text notes, yet their uncertainty estimates often

safetyarxiv-cs-cl

Hardware

DA-Cramming: Enhancing Cost-Effective Language Model Pretraining with Dependency Agreement Integration

arXiv:2311.04799v2 Announce Type: replace Abstract: Pretraining language models is still a challenge for many researchers due to its substantial computational costs. As such, there is growing interest

hardwarearxiv-cs-cl

HAMSA: Scanning-Free Vision State Space Models via SpectralPulseNet

arXiv:2604.14724v1 Announce Type: new Abstract: Vision State Space Models (SSMs) like Vim, VMamba, and SiMBA rely on complex scanning strategies to adapt sequential SSMs to process 2D images, introduc

LexGenius: An Expert-Level Benchmark for Large Language Models in Legal General Intelligence

arXiv:2512.04578v3 Announce Type: replace Abstract: Legal general intelligence (GI) refers to artificial intelligence (AI) that encompasses legal understanding, reasoning, and decision-making, simulat

MEBench: A Novel Benchmark for Understanding Mutual Exclusivity Bias in Vision-Language Models

model-releasesarxiv-cs-cv

arXiv:2505.20122v2 Announce Type: replace Abstract: This paper introduces MEBench, a novel benchmark for evaluating mutual exclusivity (ME) bias, a cognitive phenomenon observed in children during wor

Model-Based Reinforcement Learning Exploits Passive Body Dynamics for High-Performance Biped Robot Locomotion

arXiv:2604.14565v1 Announce Type: new Abstract: Embodiment is a significant keyword in recent machine learning fields. This study focused on the passive nature of the body of a biped robot to generate

researcharxiv-cs-ro

Predicting Post-Traumatic Epilepsy from Clinical Records using Large Language Model Embeddings

arXiv:2604.14547v1 Announce Type: new Abstract: Objective: Post-traumatic epilepsy (PTE) is a debilitating neurological disorder that develops after traumatic brain injury (TBI). Early prediction of P

researcharxiv-cs-lg