model releases

Brain-Inspired Capture: Evidence-Driven Neuromimetic Perceptual Simulation for Visual Decoding

arXiv:2604.17927v1 Announce Type: new Abstract: Visual decoding of neurophysiological signals is a critical challenge for brain-computer interfaces (BCIs) and computational neuroscience. However, curr

Model Releases

BridgeEQA: Virtual Embodied Agents for Real Bridge Inspections

DGX agent

arXiv:2511.12676v2 Announce Type: replace Abstract: Deploying embodied agents that can answer questions about their surroundings in realistic real-world settings remains difficult, partly due to the s

model-releasesarxiv-cs-cv

21 Apr 2026

Bridging the Reasoning Gap in Vietnamese with Small Language Models via Test-Time Scaling

arXiv:2604.17794v1 Announce Type: new Abstract: The democratization of ubiquitous AI hinges on deploying sophisticated reasoning capabilities on resource-constrained devices. However, Small Language M

Budget-Aware Anytime Reasoning with LLM-Synthesized Preference Data

arXiv:2601.11038v2 Announce Type: replace Abstract: We study the reasoning behavior of large language models (LLMs) under limited computation budgets. In such settings, producing useful partial soluti

CAM3DNet: Comprehensively mining the multi-scale features for 3D Object Detection with Multi-View Cameras

arXiv:2604.17024v1 Announce Type: new Abstract: Query-based 3D object detection methods using multi-view images often struggle to efficiently leverage dynamic multi-scale information, e.g., the relati

Camo-M3FD: A New Benchmark Dataset for Cross-Spectral Camouflaged Pedestrian Detection

arXiv:2604.16582v1 Announce Type: new Abstract: Pedestrian detection is fundamental to autonomous driving, robotics, and surveillance. Despite progress in deep learning, reliable identification remain

Can Large Language Models Understand Context?

model-releasesapple-ml-research

Understanding context is key to understanding human language, an ability which Large Language Models (LLMs) have been increasingly seen to demonstrate to an impressive extent. However, though the eval

Can LLM-Generated Text Empower Surgical Vision-Language Pre-training?

arXiv:2604.18134v1 Announce Type: new Abstract: Recent advancements in self-supervised learning have led to powerful surgical vision encoders capable of spatiotemporal understanding. However, extendin

Capture Timing-Attention of Events in Clinical Time Series

arXiv:2602.10385v2 Announce Type: replace Abstract: Automatically discovering personalized sequential events from large-scale time-series data is crucial for enabling precision medicine in clinical re

CARI4D: Category Agnostic 4D Reconstruction of Human-Object Interaction

arXiv:2512.11988v3 Announce Type: replace Abstract: Accurate capture of human-object interaction from ubiquitous sensors like RGB cameras is important for applications in human understanding, gaming,

CaseFacts: A Benchmark for Legal Fact-Checking and Precedent Retrieval

arXiv:2601.17230v2 Announce Type: replace Abstract: Automated Fact-Checking has largely focused on verifying general knowledge against static corpora, overlooking high-stakes domains like law where tr

CATP: Confidence-Aware Token Pruning for Camouflaged Object Detection

arXiv:2604.16854v1 Announce Type: new Abstract: Camouflaged Object Detection (COD) aims to segment targets that share extreme textural and structural similarities with their complex environments. Leve

CaTS-Bench: Can Language Models Describe Time Series?

arXiv:2509.20823v5 Announce Type: replace-cross Abstract: Time series captioning, the task of describing time series in natural language, requires numeric and temporal reasoning, trend interpretation,

CBRS: Cognitive Blood Request System with Bilingual Dataset and Dual-Layer Filtering for Multi-Platform Social Streams

arXiv:2604.16665v1 Announce Type: new Abstract: Urgent blood donation seeking posts and messages on social media often go unnoticed due to the overwhelming volume of daily communications. Traditional

CDSA-Net:Collaborative Decoupling of Vascular Structure and Background for High-Fidelity Coronary Digital Subtraction Angiography

arXiv:2604.17208v1 Announce Type: new Abstract: Digital subtraction angiography (DSA) in coronary imaging is fundamentally challenged by physiological motion, forcing reliance on raw angiograms clutte

CFMS: Towards Explainable and Fine-Grained Chinese Multimodal Sarcasm Detection Benchmark

arXiv:2604.16372v1 Announce Type: new Abstract: Multimodal sarcasm detection has recently garnered significant attention. However, existing benchmarks suffer from coarse-grained annotations and limite

Chain Of Interaction Benchmark (COIN): When Reasoning meets Embodied Interaction

model-releasesarxiv-cs-ro

arXiv:2604.16886v1 Announce Type: new Abstract: Generalist embodied agents must perform interactive, causally-dependent reasoning, continually interacting with the environment, acquiring information,

Channel Attention-Guided Cross-Modal Knowledge Distillation for Referring Image Segmentation

arXiv:2604.16806v1 Announce Type: new Abstract: Referring image segmentation (RIS) requires accurate segmentation of target regions in images according to language descriptions, which is a cross-modal

Chatting about Upper-Body Expressive Human Pose and Shape Estimation

arXiv:2604.17959v1 Announce Type: new Abstract: Expressive Human Pose and Shape Estimation (EHPS) plays a crucial role in various AR/VR applications and has witnessed significant progress in recent ye

Claude Opus 4.7 with adaptive thinking via the API... am I missing something or is it not possible any more to force it to think? (Prompt ha…

model-releasessimon-willison--x

Claude Opus 4.7 with adaptive thinking via the API... am I missing something or is it not possible any more to force it to think? (Prompt hacks like 'think step by step' don't count here, I mean the e

ClawEnvKit: Automatic Environment Generation for Claw-Like Agents

arXiv:2604.18543v1 Announce Type: cross Abstract: Constructing environments for training and evaluating claw-like agents remains a manual, human-intensive process that does not scale. We argue that wh

CodePivot: Bootstrapping Multilingual Transpilation in LLMs via Reinforcement Learning without Parallel Corpora

arXiv:2604.18027v1 Announce Type: cross Abstract: Transpilation, or code translation, aims to convert source code from one programming language (PL) to another. It is beneficial for many downstream ap

CoDial: Interpretable Task-Oriented Dialogue Systems Through Dialogue Flow Alignment

arXiv:2506.02264v3 Announce Type: replace Abstract: Building Task-Oriented Dialogue (TOD) systems that generalize across different tasks remains a challenging problem. Data-driven approaches often str

Cognitive Chain-of-Thought (CoCoT): Structured Multimodal Reasoning about Social Situations

arXiv:2507.20409v2 Announce Type: replace Abstract: Chain-of-Thought (CoT) prompting helps models think step by step. But naive CoT breaks down in visually grounded social tasks, where models must per

CoLLM: A Unified Framework for Co-execution of LLMs Federated Fine-tuning and Inference

arXiv:2604.16400v1 Announce Type: cross Abstract: As Large Language Models (LLMs) are increasingly adopted in edge intelligence to power domain-specific applications and personalized services, the qua

Combined Hyperbolic and Euclidean Soft Triple Loss Beyond the Single Space Deep Metric Learning

arXiv:2510.05643v2 Announce Type: replace Abstract: Deep metric learning (DML) aims to learn a neural network mapping data to an embedding space, which can represent semantic similarity between data p

ComPASS: Towards Personalized Agentic Social Support via Tool-Augmented Companionship

arXiv:2604.18356v1 Announce Type: new Abstract: Developing compassionate interactive systems requires agents to not only understand user emotions but also provide diverse, substantive support. While r

Complex normalizing flows can be information Kahler-Ricci flows

arXiv:2604.17954v1 Announce Type: cross Abstract: We develop interconnections between the complex normalizing flow for data drawn from Borel probability measures on the twofold realification of the co

Concurrent Criterion Validation of a Validity Screen for LLM Confidence Signals via Selective Prediction

arXiv:2604.17716v1 Announce Type: new Abstract: The validity screen (Cacioli, 2026d, 2026e) classifies LLM confidence signals as Valid, Indeterminate, or Invalid. We test whether these classifications

Conditional Attribution for Root Cause Analysis in Time-Series Anomaly Detection

arXiv:2604.17616v1 Announce Type: new Abstract: Root cause analysis (RCA) for time-series anomaly detection is critical for the reliable operation of complex real-world systems. Existing explanation m

Conformal Risk Control under Non-Monotone Losses: Theory and Finite-Sample Guarantees

arXiv:2604.01502v2 Announce Type: replace-cross Abstract: Conformal risk control (CRC) provides distribution-free guarantees for controlling the expected loss at a user-specified level. Existing theor

ConMeZO: Adaptive Descent-Direction Sampling for Gradient-Free Finetuning of Large Language Models

arXiv:2511.02757v2 Announce Type: replace Abstract: Zeroth-order or derivative-free optimization (MeZO) is an attractive strategy for finetuning large language models (LLMs) because it eliminates the

Constructive Distortion: Improving MLLMs with Attention-Guided Image Warping

arXiv:2510.09741v3 Announce Type: replace Abstract: Multimodal large language models (MLLMs) often miss small details and spatial relations in cluttered scenes, leading to errors in fine-grained perce

Continuous Limits of Coupled Flows in Representation Learning

arXiv:2604.16801v1 Announce Type: new Abstract: While modern representation learning relies heavily on global error signals, decentralized algorithms driven by local interactions offer a fundamental d

Copy First, Translate Later: Interpreting Translation Dynamics in Multilingual Pretraining

arXiv:2604.17633v1 Announce Type: new Abstract: Large language models exhibit impressive cross-lingual capabilities. However, prior work analyzes this phenomenon through isolated factors and at sparse

CORP: A Multi-Modal Dataset for Campus-Oriented Roadside Perception Tasks

arXiv:2404.03191v3 Announce Type: replace Abstract: Numerous roadside perception datasets have been introduced to propel advancements in autonomous driving and intelligent transportation systems resea

Counterfactual Modeling with Fine-Tuned LLMs for Health Intervention Design and Sensor Data Augmentation

arXiv:2601.14590v2 Announce Type: replace Abstract: Counterfactual explanations (CFEs) provide human-centric interpretability by identifying the minimal, actionable changes required to alter a machine

Creating ConLangs to Probe the Metalinguistic Grammatical Knowledge of LLMs

arXiv:2510.07591v3 Announce Type: replace Abstract: We present a system that uses LLMs as a tool in the development of Constructed Languages -- ConLangs, which we call IASC (Interactive Agentic System

CreditDecoding: Accelerating Parallel Decoding in Diffusion Large Language Models with Trace Credit

arXiv:2510.06133v2 Announce Type: replace Abstract: Diffusion large language models (dLLMs) generate text through iterative denoising. In commonly adopted parallel decoding schemes, each step confirms

CROC: Evaluating and Training T2I Metrics with Pseudo- and Human-Labeled Contrastive Robustness Checks

arXiv:2505.11314v2 Announce Type: replace-cross Abstract: The assessment of evaluation metrics (meta-evaluation) is crucial for determining the suitability of existing metrics in text-to-image (T2I) g

Cross-Family Speculative Decoding for Polish Language Models on Apple~Silicon: An Empirical Evaluation of Bielik~11B with UAG-Extended MLX-LM

arXiv:2604.16368v1 Announce Type: new Abstract: Speculative decoding accelerates LLM inference by using a small draft model to propose k candidate tokens for a target model to verify. While effective

Cross-Modal Bayesian Low-Rank Adaptation for Uncertainty-Aware Multimodal Learning

arXiv:2604.16657v1 Announce Type: new Abstract: Large pre-trained language models are increasingly adapted to downstream tasks using parameter-efficient fine-tuning (PEFT), but existing PEFT methods a

D-QRELO: Training- and Data-Free Delta Compression for Large Language Models via Quantization and Residual Low-Rank Approximation

arXiv:2604.16940v1 Announce Type: new Abstract: Supervised Fine-Tuning (SFT) accelerates taskspecific large language models (LLMs) development, but the resulting proliferation of finetuned models incu

DART: Mitigating Harm Drift in Difference-Aware LLMs via Distill-Audit-Repair Training

arXiv:2604.16845v1 Announce Type: new Abstract: Large language models (LLMs) tuned for safety often avoid acknowledging demographic differences, even when such acknowledgment is factually correct (e.g

Deep Learning-Enhanced Calibration of the Heston Model: A Unified Framework

arXiv:2510.24074v2 Announce Type: replace-cross Abstract: The Heston stochastic volatility model is a widely used tool in financial mathematics for pricing European options. However, its calibration r

Deep Learning for Virtual Reality User Identification: A Benchmark

arXiv:2604.16341v1 Announce Type: cross Abstract: Virtual Reality (VR) applications require robust user identification systems to ensure secure access to equipment and protect worker identities. Motio

DEM Refinement and Validation on the Lunar Surface Using Shape-from-Shading with Chandrayaan-2 OHRC Imagery

arXiv:2604.17436v1 Announce Type: new Abstract: This study presents a Shape from Shading (SfS) framework to enhance sub-metre resolution lunar digital elevation models (DEMs) using imagery from the Or

Depth Registers Unlock W4A4 on SwiGLU: A Reader/Generator Decomposition

arXiv:2604.18128v1 Announce Type: new Abstract: We study post-training W4A4 quantization in a controlled 300M-parameter SwiGLU decoder-only language model trained on 5B tokens of FineWeb-Edu, and ask