Search: “model-releases”

CALYREX: Cross-Attention LaYeR EXtended Transformers for System Prompt Anchoring

arXiv:2605.09737v1 Announce Type: new Abstract: Modern large language models (LLMs) rely on system prompts to establish behavioral constraints and safety rules. Standard causal self-attention treats p

Model Releases

Can Agent Benchmarks Support Their Scores? Evidence-Supported Bounds for Interactive-Agent Evaluation

DGX agent

arXiv:2605.10448v1 Announce Type: new Abstract: Interactive agent benchmarks map an agent run to a binary outcome through outcome checks. When these checks rely on surface level signals or fail to cap

model-releasesarxiv-cs-ai

12 May 2026

Can Deep Research Agents Retrieve and Organize? Evaluating the Synthesis Gap with Expert Taxonomies

arXiv:2601.12369v3 Announce Type: replace Abstract: Deep Research Agents increasingly automate survey generation, yet whether they match human experts at retrieving essential papers and organizing the

Can LLMs Predict Polymer Physics Just by Reading Synthesis and Processing Prose?

arXiv:2605.08255v1 Announce Type: cross Abstract: Can large language models predict physical and mechanical polymer properties simply by reading unstructured scientific prose? Polymer performance is r

Can We Go Beyond Visual Features? Neural Tissue Relation Modeling for Relational Graph Analysis in Non-Melanoma Skin Histology

model-releasesarxiv-cs-cv

arXiv:2512.06949v3 Announce Type: replace Abstract: Histopathology image segmentation is essential for delineating tissue structures in skin cancer diagnostics, but modeling spatial context and inter-

Can We Trust LLMs for Mental Health Screening? Consistency, ASR Robustness, and Evidence Faithfulness

arXiv:2605.09634v1 Announce Type: new Abstract: LLMs can estimate Hospital Anxiety and Depression Scale (HADS) scores from speech in a zero-shot manner, but clinical deployment requires reliability ac

Capacity-Aware Inference: Mitigating the Straggler Effect in Mixture of Experts

arXiv:2503.05066v5 Announce Type: replace-cross Abstract: The Mixture of Experts (MoE) is an effective architecture for scaling large language models by leveraging sparse expert activation to balance

CapVector: Learning Transferable Capability Vectors in Parametric Space for Vision-Language-Action Models

model-releasesarxiv-cs-cv

arXiv:2605.10903v1 Announce Type: new Abstract: This paper proposes a novel approach to address the challenge that pretrained VLA models often fail to effectively improve performance and reduce adapta

Causal Dimensionality of Transformer Representations: Measurement, Scaling, and Layer Structure

arXiv:2605.08740v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) decompose transformer residual streams into interpretable feature dictionaries, yet the relationship between SAE width and

Causal Stories from Sensor Traces: Auditing Epistemic Overreach in LLM-Generated Personal Sensing Explanations

arXiv:2605.08590v1 Announce Type: cross Abstract: LLMs are increasingly used to explain personal sensing data, translating traces of activity and mood into natural-language accounts of why an anomalou

Cavity-Enhanced Collective Quantum Processing with Polarization-Encoded Qubits

arXiv:2605.10473v1 Announce Type: cross Abstract: We introduce a cavity-enhanced optical architecture for collective quantum processing in which logical qubits are encoded in the polarization subspace

CERSA: Cumulative Energy-Retaining Subspace Adaptation for Memory-Efficient Fine-Tuning

arXiv:2605.08174v1 Announce Type: cross Abstract: To mitigate the memory constraints associated with fine-tuning large pre-trained models, existing parameter-efficient fine-tuning (PEFT) methods, such

CHAINTRIX: A multi-pipeline LLM-augmented framework for automated smart-contract security auditing

arXiv:2605.09350v1 Announce Type: new Abstract: Smart-contract exploits have caused billions of USD in cumulative losses, yet audits remain expensive and slow. Automated tools have emerged to close th

ChaosNetBench: Benchmarking Spatio-Temporal Graph Neural Networks on Chaotic Lattice Dynamics

arXiv:2605.09676v1 Announce Type: cross Abstract: Spatio-temporal graph neural networks (STGNNs) are widely used for short-term forecasting in dynamic physical systems such as traffic and weather. How

Character-Level Transformer for Tajik-Persian Transliteration with a Parallel Lexical Corpus

arXiv:2605.09092v1 Announce Type: new Abstract: This study addresses automatic transliteration from Tajik (Cyrillic script) to Persian (Perso-Arabic script). We present a curated, lexicographically ve

ChartDiff: A Large-Scale Benchmark for Comprehending Pairs of Charts

arXiv:2603.28902v2 Announce Type: replace Abstract: Charts are central to analytical reasoning, yet existing benchmarks for chart understanding focus almost exclusively on single-chart interpretation

ChatbotManip: A Dataset to Facilitate Evaluation and Oversight of Manipulative Chatbot Behaviour

arXiv:2506.12090v2 Announce Type: replace Abstract: This paper introduces ChatbotManip, a novel dataset for studying manipulation in Chatbots. It contains simulated generated conversations between a c

Chinese Cyberbullying Detection: Dataset, Method, and Validation

arXiv:2505.20654v2 Announce Type: replace-cross Abstract: Existing cyberbullying detection benchmarks were organized by the polarity of speech, such as 'offensive' and 'non-offensive', which were esse

CIVeX: Causal Intervention Verification for Language Agents

arXiv:2605.09168v1 Announce Type: new Abstract: A valid tool call is not necessarily a valid intervention. Tool-using language agents are guarded by schema validators, policy filters, provenance check

Classification-Head Bias in Class-Level Machine Unlearning: Diagnosis, Mitigation, and Evaluation

arXiv:2605.08730v1 Announce Type: new Abstract: Class-level machine unlearning aims to remove the influence of specified classes while preserving model utility on retained classes. Existing methods ar

🤩🤯🤩 Claude Code (still not AGI but biggest advance since GPT-4) is the most neurosymbolic thing I have ever seen in my life. 53 symbolic …

model-releasesgary-marcus--x

🤩🤯🤩 Claude Code (still not AGI but biggest advance since GPT-4) is the most neurosymbolic thing I have ever seen in my life. 53 symbolic tools, 500,000 lines of symbolic code, combined with a state-of

Claude Opus 4.7 (fast mode) is now available in Windsurf! Full Claude Opus 4.7 intelligence ~2.5x higher output speeds We can't wait to see …

model-releaseswindsurf--x

Windsurf has released Claude Opus 4.7 in fast mode, offering the full intelligence of Claude Opus 4.7 with approximately 2.5x faster output speeds. This integration allows users of Windsurf to access

CLEF: EEG Foundation Model for Learning Clinical Semantics

arXiv:2605.10817v1 Announce Type: new Abstract: Clinical EEG interpretation requires reasoning over full EEG sessions and integrating signal patterns with clinical context. Existing EEG foundation mod

Clin-JEPA: A Multi-Phase Co-Training Framework for Joint-Embedding Predictive Pretraining on EHR Patient Trajectories

arXiv:2605.10840v1 Announce Type: cross Abstract: We present Clin-JEPA, a multi-phase co-training framework for joint-embedding predictive (JEPA) pretraining on EHR patient trajectories. JEPA architec

CLR-voyance: Reinforcing Open-Ended Reasoning for Inpatient Clinical Decision Support with Outcome-Aware Rubrics

arXiv:2605.09584v1 Announce Type: cross Abstract: Inpatient clinical reasoning is a sequential decision under partial observability: the clinician sees the admission so far and must choose the next ac

CMKL: Modality-Aware Continual Learning for Evolving Biomedical Knowledge Graphs

arXiv:2605.10510v1 Announce Type: cross Abstract: Biomedical knowledge graphs are increasingly large, dynamic, and multimodal, driven by rapid advances in biotechnology such as high-throughput sequenc

CNSocialDepress: A Chinese Social Media Dataset for Depression Risk Detection and Structured Analysis

arXiv:2510.11233v3 Announce Type: replace Abstract: Depression is a pressing global public health issue, yet publicly available Chinese-language resources for depression risk detection remain scarce a

CodeClinic: Evaluating Automation of Coding Skills for Clinical Reasoning Agents

arXiv:2605.09675v1 Announce Type: new Abstract: Clinical reasoning agents based on large language models (LLMs) aim to automate tasks such as intensive care unit (ICU) monitoring and patient state tra

CoDistill-GRPO: A Co-Distillation Recipe for Efficient Group Relative Policy Optimization

arXiv:2605.08873v1 Announce Type: new Abstract: Group Relative Policy Optimization (GRPO) has emerged as a powerful algorithm for improving the reasoning capabilities of language models, but often fai

Collective Alignment in LLM Multi-Agent Systems: Disentangling Bias from Cooperation via Statistical Physics

arXiv:2605.10528v1 Announce Type: cross Abstract: We investigate the emergent collective dynamics of LLM-based multi-agent systems on a 2D square lattice and present a model-agnostic statistical-physi

ColorConceptBench: A Benchmark for Probabilistic Color-Concept Understanding in Text-to-Image Models

arXiv:2601.16836v3 Announce Type: replace-cross Abstract: Text-to-image (T2I) models have advanced considerably in generating high-quality images from textual descriptions. However, their ability to a

CoLVR: Enhancing Exploratory Latent Visual Reasoning via Contrastive Optimization

model-releasesarxiv-cs-cv

arXiv:2605.08802v1 Announce Type: new Abstract: Due to the potential for exploratory reasoning of Latent Visual Reasoning, recent works tend to enable MLLMs (Multimodal Large Language Models) to perfo

Combining Mechanical and Agentic Specification Inference for Move

arXiv:2605.10005v1 Announce Type: cross Abstract: In this paper, we describe early work on a specification inference tool for the Move Prover that combines a weakest-precondition (WP) analysis over Mo

ComfyUI Support for HiDream-01-Image Released

model-releasesr-stablediffusion

ComfyUI support for HiDream-O1-Image enables local image generation with text prompts and optional reference images, featuring various precision options (BF16/FP16/FP32/FP8) and integration with atten

Communication Dynamics Neural Networks: FFT-Diagonalized Layers for Improved Hessian Conditioning at Reduced Parameter Count

arXiv:2605.08171v1 Announce Type: cross Abstract: Background and motivation. The Communication Dynamics (CD) framework, introduced in two earlier papers for atomic-energy prediction and field-induced

Compander-Aligned Query Geometry for Quantized Zeroth-Order Optimization

arXiv:2605.10673v1 Announce Type: new Abstract: Low-bit forward evaluation is an attractive route to memory-efficient zeroth-order (ZO) adaptation: the optimizer needs only scalar losses, and the mode

Complex-Valued Phase-Coherent Transformer

arXiv:2605.10123v1 Announce Type: new Abstract: Complex-valued Transformers have largely inherited softmax attention from real-valued architectures. However, row-normalised token competition is not ne

ComplexMCP: Evaluation of LLM Agents in Dynamic, Interdependent, and Large-Scale Tool Sandbox

arXiv:2605.10787v1 Announce Type: new Abstract: Current LLM agents are proficient at calling isolated APIs but struggle with the 'last mile' of commercial software automation. In real-world scenarios,

Compressed Video Aggregator: Content-driven Module for Efficient Micro-Video Recommendation

arXiv:2605.08810v1 Announce Type: cross Abstract: We propose Compressed Video Aggregator (CVA), a lightweight micro-video recommendation module that decouples video information from preference learnin

Computer Use at the Edge of the Statistical Precipice

arXiv:2605.08261v1 Announce Type: cross Abstract: Evaluating Computer Use Agents (CUAs) on interactive environments is fraught with methodological pitfalls that the field has yet to systematically add

Concordia: Self-Improving Synthetic Tables for Federated LLMs

arXiv:2605.09855v1 Announce Type: new Abstract: Federated learning (FL) enables training large language models (LLMs) without sharing raw data, but adapting LLMs under strict data isolation and non-II

Confidence-Guided Diffusion Augmentation for Enhanced Bangla Compound Character Recognition

arXiv:2605.10916v1 Announce Type: cross Abstract: Recognition of handwritten Bangla compound characters remains a challenging problem due to complex character structures, large intra-class variation,

ConFit v3: Improving Resume-Job Matching with LLM-based Re-Ranking

arXiv:2605.09760v1 Announce Type: new Abstract: A reliable resume-job matching system helps a company find suitable candidates from a pool of resumes and helps a job seeker find relevant jobs from a l

ConQuR: Corner Aligned Activation Quantization via Optimized Rotations for LLMs

arXiv:2605.10793v1 Announce Type: new Abstract: Large language models (LLMs) are costly to deploy due to their large memory footprint and high inference cost. Weight-activation quantization can reduce

Context-Augmented Code Generation: How Product Context Improves AI Coding Agent Decision Compliance by 49%

arXiv:2605.08112v1 Announce Type: cross Abstract: AI coding agents powered by large language models can read codebases and produce functional code, but they routinely violate team-specific product dec

Continual Harness: Online Adaptation for Self-Improving Foundation Agents

arXiv:2605.09998v1 Announce Type: cross Abstract: Coding harnesses such as Claude Code and OpenHands wrap foundation models with tools, memory, and planning, but no equivalent exists for embodied agen

Continuous Latent Contexts Enable Efficient Online Learning in Transformers

arXiv:2605.09867v1 Announce Type: cross Abstract: Large language models (LLMs) exhibit a strong capacity for in-context learning: Given labeled examples, they can generate good predictions without par

Convergence Analysis of Newton's Method for Neural Networks in the Overparameterized Limit

arXiv:2605.08352v1 Announce Type: new Abstract: A convergence analysis is developed for the regularized Newton method for training neural networks (NNs) in the overparameterized limit. As the number o