Search: “models”

TeleEmbedBench: A Multi-Corpus Embedding Benchmark for RAG in Telecommunications

arXiv:2604.17778v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed in the telecommunications domain for critical tasks, relying heavily on Retrieval-Augmented Gener

21 Apr 2026

Model Releases

Towards a Data-Parameter Correspondence for LLMs: A Preliminary Discussion

DGX agent

arXiv:2604.17384v1 Announce Type: new Abstract: Large language model optimization has historically bifurcated into isolated data-centric and model-centric paradigms: the former manipulates involved sa

model-releasesarxiv-cs-lg

21 Apr 2026

Video Panels for Long Video Understanding

model-releasesarxiv-cs-cv

arXiv:2509.23724v2 Announce Type: replace Abstract: Recent Video-Language Models (VLMs) achieve promising results on long-video understanding, but their performance still lags behind that achieved on

21 Apr 2026

When Helpers Become Hazards: A Benchmark for Analyzing Multimodal LLM-Powered Safety in Daily Life

arXiv:2601.04043v2 Announce Type: replace Abstract: As Multimodal Large Language Models (MLLMs) become an indispensable assistant in human life, the unsafe content generated by MLLMs poses a danger to

21 Apr 2026

Agents

AgentV-RL: Scaling Reward Modeling with Agentic Verifier

arXiv:2604.16004v1 Announce Type: cross Abstract: Verifiers have been demonstrated to enhance LLM reasoning via test-time scaling (TTS). Yet, they face significant challenges in complex domains. Error

agentsarxiv-cs-ai

Exploring LLM-based Verilog Code Generation with Data-Efficient Fine-Tuning and Testbench Automation

model-releasesarxiv-cs-ai

arXiv:2604.15388v1 Announce Type: cross Abstract: Recent advances in large language models have improved code generation, but their use in hardware description languages is still limited. Moreover, tr

FS-Researcher: Test-Time Scaling for Long-Horizon Research Tasks with File-System-Based Agents

arXiv:2602.01566v2 Announce Type: replace Abstract: Deep research is emerging as a representative long-horizon task for large language model (LLM) agents. However, long trajectories in deep research o

LACE: Lattice Attention for Cross-thread Exploration

arXiv:2604.15529v1 Announce Type: new Abstract: Current large language models reason in isolation. Although it is common to sample multiple reasoning paths in parallel, these trajectories do not inter

OjaKV: Context-Aware Online Low-Rank KV Cache Compression

model-releasesarxiv-cs-ai

arXiv:2509.21623v2 Announce Type: replace-cross Abstract: The expanding long-context capabilities of large language models are constrained by a significant memory bottleneck: the key-value (KV) cache

Ollama we love you 👨‍💻🚀

Ollama we love you 👨‍💻🚀 Kimi K2.6 raises the bar for open-source models. 🦙 available on Ollama's cloud! Try it with OpenClaw: ollama launch openclaw --model kimi-k2.6:cloud Try it with Hermes Agent: o

model-releasesollama--x

OSCBench: Benchmarking Object State Change in Text-to-Video Generation

model-releasesarxiv-cs-ai

arXiv:2603.11698v2 Announce Type: replace-cross Abstract: Text-to-video (T2V) generation models have made rapid progress in producing visually high-quality and temporally coherent videos. However, exi

Persona-Assigned Large Language Models Exhibit Human-Like Motivated Reasoning

arXiv:2506.20020v2 Announce Type: replace Abstract: Reasoning in humans is prone to biases due to underlying motivations like identity protection, that undermine rational decision-making and judgment.

safetyarxiv-cs-ai

Privacy-Preserving LLMs Routing

arXiv:2604.15728v1 Announce Type: cross Abstract: Large language model (LLM) routing has emerged as a critical strategy to balance model performance and cost-efficiency by dynamically selecting servic

Sample Complexity Bounds for Stochastic Shortest Path with a Generative Model

arXiv:2604.16111v1 Announce Type: new Abstract: We study the sample complexity of learning an epsilon-optimal policy in the Stochastic Shortest Path (SSP) problem. We first derive sample complexity bo

Scaling Behaviors of LLM Reinforcement Learning Post-Training: An Empirical Study in Mathematical Reasoning

arXiv:2509.25300v4 Announce Type: replace-cross Abstract: While scaling laws for large language models (LLMs) during pre-training have been extensively studied, their behavior under reinforcement lear

Synthetic data in cryptocurrencies using generative models

arXiv:2604.16182v1 Announce Type: cross Abstract: Data plays a fundamental role in consolidating markets, services, and products in the digital financial ecosystem. However, the use of real data, espe

Hardware

Taming Asynchronous CPU-GPU Coupling for Frequency-aware Latency Estimation on Mobile Edge

arXiv:2604.15357v1 Announce Type: cross Abstract: Precise estimation of model inference latency is crucial for time-critical mobile edge applications, enabling devices to calculate latency margins aga

hardwarearxiv-cs-ai

TriagerX: Dual Transformers for Bug Triaging Tasks with Content and Interaction Based Rankings

arXiv:2508.16860v2 Announce Type: replace-cross Abstract: Pretrained Language Models or PLMs are transformer-based architectures that can be used in bug triaging tasks. PLMs can better capture token s

applicationsarxiv-cs-ai

easyaligner: Forced alignment with GPU acceleration and flexible text normalization (compatible with all w2v2 models on HF Hub) [P]

easyaligner is a forced alignment library designed to be performant and easy to use , leveraging GPU acceleration to align audio with text transcriptions. The tool supports flexible text normalization

safetyr-machinelearning

18 Apr 2026

Paper from Kimi: Prefill-as-a-Service: KVCache of Next-Generation Models Could Go Cross-Datacenter [R]

researchr-machinelearning

Mooncake is the serving platform for Kimi developed by Moonshot AI, featuring a KVCache-centric disaggregated architecture that separates prefill and decoding clusters while leveraging underutilized C

18 Apr 2026

A Robust Approach for LiDAR-Inertial Odometry Without Sensor-Specific Modeling

arXiv:2509.06593v2 Announce Type: replace Abstract: Accurate odometry is a critical component in a robotic navigation stack, and subsequent modules such as planning and control often rely on an estima

researcharxiv-cs-ro

Local Ai

BitFlipScope: Scalable Fault Localization and Recovery for Bit-Flip Corruptions in LLMs

arXiv:2512.22174v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) deployed in practical and safety-critical settings are increasingly susceptible to bit-flip faults caused by hard

local-aiarxiv-cs-ai

Bridging the Gap between Learning and Inference for Diffusion-Based Molecule Generation

arXiv:2411.05472v2 Announce Type: replace Abstract: The paradigm shift toward structure-driven molecule generation has been propelled by advances in deep generative models, such as variational auto-en

Calibrate-Then-Delegate: Safety Monitoring with Risk and Budget Guarantees via Model Cascades

arXiv:2604.14251v1 Announce Type: new Abstract: Monitoring LLM safety at scale requires balancing cost and accuracy: a cheap latent-space probe can screen every input, but hard cases should be escalat

Can LLMs Score Medical Diagnoses and Clinical Reasoning as well as Expert Panels?

arXiv:2604.14892v1 Announce Type: new Abstract: Evaluating medical AI systems using expert clinician panels is costly and slow, motivating the use of large language models (LLMs) as alternative adjudi

DeepPrune: Parallel Scaling without Inter-trace Redundancy

arXiv:2510.08483v2 Announce Type: replace Abstract: Parallel scaling has emerged as a powerful paradigm to enhance reasoning capabilities in large language models (LLMs) by generating multiple Chain-o

researcharxiv-cs-cl

DPQuant: Efficient and Differentially-Private Model Training via Dynamic Quantization Scheduling

arXiv:2509.03472v2 Announce Type: replace Abstract: Differentially-Private SGD (DP-SGD) and its adaptive variant DP-Adam are powerful techniques to protect user privacy when using sensitive data to tr

Language Model as Planner and Formalizer under Constraints

arXiv:2510.05486v2 Announce Type: replace Abstract: LLMs have been widely used in planning, either as planners to generate action sequences end-to-end, or as formalizers to represent the planning doma

safetyarxiv-cs-cl

OmniLight: One Model to Rule All Lighting Conditions

arXiv:2604.15170v1 Announce Type: new Abstract: Adverse lighting conditions, such as cast shadows and irregular illumination, pose significant challenges to computer vision systems by degrading visibi

applicationsarxiv-cs-cv

SAGE: Sign-Adaptive Gradient for Memory-Efficient LLM Optimization

arXiv:2604.07663v2 Announce Type: replace Abstract: The AdamW optimizer, while standard for LLM pretraining, is a critical memory bottleneck, consuming optimizer states equivalent to twice the model's

Scalable Model-Based Clustering with Sequential Monte Carlo

arXiv:2604.14810v1 Announce Type: cross Abstract: In online clustering problems, there is often a large amount of uncertainty over possible cluster assignments that cannot be resolved until more data

Unsupervised Learning of Local Updates for Maximum Independent Set in Dynamic Graphs

arXiv:2505.13754v3 Announce Type: replace Abstract: We present the first unsupervised learning model for Maximum-Independent-Set (MaxIS) in dynamic graphs where edges change over time. Our method comb

Blind Bitstream-corrupted Video Recovery via Metadata-guided Diffusion Model

arXiv:2604.13906v1 Announce Type: new Abstract: Bitstream-corrupted video recovery aims to restore realistic content degraded during video storage or transmission. Existing methods typically assume th

applicationsarxiv-cs-cv

Caption First, VQA Second: Knowledge Density, Not Task Format, Drives Multimodal Scaling

arXiv:2604.13054v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) have achieved rapid progress, yet their scaling behavior remains less clearly characterized and often less pred

researcharxiv-cs-cl

Getting the Numbers Rightnicode{x2014}Modelling Multi-Class Object Counting in Dense and Varied Scenes

arXiv:2510.02213v2 Announce Type: replace Abstract: Density map estimation enables accurate object counting in heavily occluded, and densely packed scenes where detection-based counting fails. In mult

researcharxiv-cs-cv

Graph Propagated Projection Unlearning: A Unified Framework for Vision and Audio Discriminative Models

arXiv:2604.13127v1 Announce Type: new Abstract: The need to selectively and efficiently erase learned information from deep neural networks is becoming increasingly important for privacy, regulatory c

researcharxiv-cs-cv

Hessian-Enhanced Token Attribution (HETA): Interpreting Autoregressive LLMs

arXiv:2604.13258v1 Announce Type: new Abstract: Attribution methods seek to explain language model predictions by quantifying the contribution of input tokens to generated outputs. However, most exist

Monthly Diffusion v0.9: A Latent Diffusion Model for the First AI-MIP

arXiv:2604.13481v1 Announce Type: new Abstract: Here, we describe Monthly Diffusion at 1.5-degree grid spacing (MD-1.5 version 0.9), a climate emulator that leverages a spherical Fourier neural operat

Neural Mean-Field Games: Extending Mean-Field Game Theory with Neural Stochastic Differential Equations

arXiv:2504.13228v4 Announce Type: replace Abstract: Mean-field game theory relies on approximating games that are intractable to model due to a very large to infinite population of players. While thes

SpatialEvo: Self-Evolving Spatial Intelligence via Deterministic Geometric Environments

arXiv:2604.14144v1 Announce Type: cross Abstract: Spatial reasoning over three-dimensional scenes is a core capability for embodied intelligence, yet continuous model improvement remains bottlenecked

The cognitive companion: a lightweight parallel monitoring architecture for detecting and recovering from reasoning degradation in LLM agents

arXiv:2604.13759v1 Announce Type: cross Abstract: Large language model (LLM) agents on multi-step tasks suffer reasoning degradation, looping, drift, stuck states, at rates up to 30% on hard tasks. Cu

Analyzing the Effect of Noise in LLM Fine-tuning

arXiv:2604.12469v1 Announce Type: new Abstract: Fine-tuning is the dominant paradigm for adapting pretrained large language models (LLMs) to downstream NLP tasks. In practice, fine-tuning datasets may

ArtifactWorld: Scaling 3D Gaussian Splatting Artifact Restoration via Video Generation Models

arXiv:2604.12251v1 Announce Type: new Abstract: 3D Gaussian Splatting (3DGS) delivers high-fidelity real-time rendering but suffers from geometric and photometric degradations under sparse-view constr

applicationsarxiv-cs-cv

ASGuard: Activation-Scaling Guard to Mitigate Targeted Jailbreaking Attack

arXiv:2509.25843v2 Announce Type: replace Abstract: Large language models (LLMs), despite being safety-aligned, exhibit brittle refusal behaviors that can be circumvented by simple linguistic changes.

safetyarxiv-cs-ai

CoLA: A Choice Leakage Attack Framework to Expose Privacy Risks in Subset Training

arXiv:2604.12342v1 Announce Type: cross Abstract: Training models on a carefully chosen portion of data rather than the full dataset is now a standard preprocess for modern ML. From vision coreset sel

researcharxiv-cs-cv

ContextLens: Modeling Imperfect Privacy and Safety Context for Legal Compliance

arXiv:2604.12308v1 Announce Type: new Abstract: Individuals' concerns about data privacy and AI safety are highly contextualized and extend beyond sensitive patterns. Addressing these issues requires

safetyarxiv-cs-cl

Generative Refinement Networks for Visual Synthesis

model-releasesarxiv-cs-cv

arXiv:2604.13030v1 Announce Type: new Abstract: While diffusion models dominate the field of visual generation, they are computationally inefficient, applying a uniform computational effort regardless

Nucleus-Image: Sparse MoE for Image Generation

model-releasesarxiv-cs-cv

arXiv:2604.12163v1 Announce Type: new Abstract: We present Nucleus-Image, a text-to-image generation model that establishes a new Pareto frontier in quality-versus-efficiency by matching or exceeding