Search: “models”

SC3: The Multi-Solvent Solubility Challenge and Benchmark

arXiv:2606.07656v1 Announce Type: cross Abstract: Solubility prediction is a standard benchmark in computational chemistry, yet multi-solvent models which reportedly approach the experimental-noise ce

SciFlow-Bench: Evaluating Structure-Aware Scientific Diagram Generation via Inverse Parsing

DGX agent

arXiv:2602.09809v2 Announce Type: replace Abstract: Scientific diagrams convey explicit structural information, yet modern text-to-image models often produce visually plausible but structurally incorr

model-releasesarxiv-cs-cv

9 Jun 2026

Local Ai

Self-Consistent Generative Paths via Admissible Random Variational Transport

arXiv:2606.08953v1 Announce Type: new Abstract: Modern generative models often define an entire probability path from a simple prior to the data law, rather than only an endpoint map. Diffusion models

local-aiarxiv-cs-lg

Shared Latent Structures Enable Unified Backdoor Detection and Mitigation in LLMs

arXiv:2606.07963v1 Announce Type: new Abstract: Backdoor attacks in large language models (LLMs) are often treated as isolated trigger-response failures, motivating defenses tailored to specific trigg

Shared Semantics, Divergent Mechanisms: Unsupervised Feature Discovery by Aligning Semantics and Mechanisms

arXiv:2606.08236v1 Announce Type: cross Abstract: As large language models are increasingly deployed in high-stakes settings, there is a growing need for tools that audit not only model outputs but al

SNN-MLIR: An MLIR Dialect for Compiling Neuromorphic SNNs from NIR to Bare-Metal C

arXiv:2606.09213v1 Announce Type: cross Abstract: Spiking neural networks (SNNs) are increasingly trained in a wide range of frameworks (SnnTorch, Lava, Norse, and others) each with its own model form

Sovereign AI for all.

Cohere advocates for democratizing access to sovereign AI systems, enabling organizations and nations to develop and deploy their own AI models independently rather than relying on centralized provide

model-releasescohere--x

SpectrumKV: Per-Token Mixed-Precision KV Cache Transfer for Prefill-Decode Disaggregated LLM Serving

arXiv:2606.08635v1 Announce Type: new Abstract: Prefill-decode (PD) disaggregation decouples prompt processing from token generation, but it also turns the key-value (KV) cache into a network payload.

Safety

Steganography Without Modification: Hidden Communication via LLM Seeds

arXiv:2606.09135v1 Announce Type: cross Abstract: We demonstrate that widely deployed Large Language Model (LLM) inference stacks harbor a steganographic channel that requires no modification to model

safetyarxiv-cs-ai

Struct-Searcher: Agentic Structural Thinking Advances Multimodal Deep Information Seeking

arXiv:2606.07689v1 Announce Type: new Abstract: Deep research agents have attracted increasing attention for their ability to collect large-scale online information to acquire target knowledge, with r

The Injection Paradox: Brand-Level Suppression in Safety-Trained LLM Recommendations via RAG Context Injection

arXiv:2606.09204v1 Announce Type: new Abstract: We present a reproducible failure mode of safety training in RAG-based LLM recommendation -- the Injection Paradox -- in which prompt injections embedde

The Mirrored Influence Hypothesis: Efficient Data Influence Estimation by Harnessing Forward Passes

arXiv:2402.08922v3 Announce Type: replace Abstract: Large-scale black-box models have become ubiquitous across numerous applications. Understanding the influence of individual training data sources on

There has been a lot of hand wringing on the appropriate valuation of SpaceX. Some large institutions believe SpaceX can only be valued at h…

model-releaseselon-musk--x

There has been a lot of hand wringing on the appropriate valuation of SpaceX. Some large institutions believe SpaceX can only be valued at half what the market seems to be willing to pay for it. Other

TQA-Bench: Evaluating LLMs for Multi-Table Question Answering

arXiv:2411.19504v2 Announce Type: replace Abstract: The advance of large language models (LLMs) has unlocked great opportunities in complex multi-modal data management tasks, particularly in question

TRL-Bench: Standardizing Cross-Paradigm Representation-Level Evaluation of Tabular Encoders

arXiv:2606.09323v1 Announce Type: new Abstract: Tabular encoders are usually evaluated inside task-specific end-to-end pipelines, so models from different training paradigms are difficult to compare d

Unification of Closed-Open Industrial Detection Scenarios: New Large-Scale Benchmarks,Challenges and Baselines

arXiv:2606.07953v1 Announce Type: new Abstract: Large-scale Visual-Language Models (LVLMs) have achieved remarkable success in natural visual tasks, yet their application to industrial defect detectio

UniQL: Towards Dialect-Universal Benchmarking for Text-to-SQL

arXiv:2606.08018v1 Announce Type: new Abstract: Existing text-to-SQL benchmarks are largely centered on SQLite, making it difficult to evaluate whether models can generalize across heterogeneous SQL d

VFEM: Visual Feature Empowered Multivariate Time Series Forecasting with Cross-Modal Fusion

arXiv:2510.03244v2 Announce Type: replace-cross Abstract: Large time series foundation models often adopt channel-independent architectures to handle varying data dimensions, but this design ignores c

researcharxiv-cs-ai

We've got 13 days to burn as much tokens as humanly possible on Claude Max plans Before they revert to API based billing 💀

model-releasesjerry-liu--x

We've got 13 days to burn as much tokens as humanly possible on Claude Max plans Before they revert to API based billing 💀 Introducing Claude Fable 5: a Mythos-class model that we’ve made safe for gen

A Geometric Gaussian Mixture Representation of Plane Curves

arXiv:2606.06505v1 Announce Type: cross Abstract: We introduce a user defined probabilistic polygonal representation for plane curves. Given a curve, we select vertices on the curve and connect consec

Act As a Real Researcher: A Suite of Benchmarks Evaluating Frontier LLMs and Agentic Harnesses in Research Lifecycle

arXiv:2606.07462v1 Announce Type: new Abstract: As foundation models advance and agent scaffolding becomes increasingly sophisticated, agents have demonstrated remarkable proficiency in complex, long-

From Sampled Outcomes to Capability Distributions: Rethinking Supervision for LLM Routing

arXiv:2606.06924v1 Announce Type: new Abstract: Existing LLM routing methods typically treat a model's single response to a query as its capability label for training routers. However, because LLM gen

Generative Molecular Morphing for Flexible-Size Design via Unbalanced Optimal Transport

arXiv:2606.07239v1 Announce Type: new Abstract: The success of generative molecular design hinges on a model's steerability toward high-reward samples. Because many molecular properties are intrinsica

Hierarchical Certified Semantic Commitment for Byzantine-Resilient LLM-Agent Collaboration

arXiv:2606.07316v1 Announce Type: cross Abstract: Byzantine collaboration among large-language-model agents requires a finality-control primitive: given delivered stochastic, structured natural-langua

Hierarchical Semantic-Constrained Heterogeneous Graph for Audio-Visual Event Localization

arXiv:2606.07033v1 Announce Type: new Abstract: Open-vocabulary audio-visual event localization (OV-AVEL) jointly models audio-visual cues to recognize and temporally localize events, including catego

Improving Cross-Lingual Factual Recall via Consistency-Driven Reinforcement Learning

model-releasesarxiv-cs-cl

arXiv:2606.06586v1 Announce Type: new Abstract: Large language models (LLMs) trained predominantly on English data encode substantial world knowledge, yet often fail to express it reliably in other la

It's a TRAP! Task-Redirecting Agent Persuasion Benchmark for Web Agents

arXiv:2512.23128v2 Announce Type: replace-cross Abstract: Web-based agents powered by large language models are increasingly used for tasks such as email management or professional networking. Their r

MemDreamer: Decoupling Perception and Reasoning for Long Video Understanding via Hierarchical Graph Memory and Agentic Retrieval Mechanism

arXiv:2606.07512v1 Announce Type: cross Abstract: Current Vision-Language Models struggle with hours-long videos because processing full-length visual sequences induces prohibitive token explosion and

Safety

Online Pandora's Box for Contextual LLM Cascading

arXiv:2606.07392v1 Announce Type: new Abstract: Motivated by Large Language Model (LLM) cascading, we propose an online contextual Pandora's Box model for adaptively querying and selecting LLM APIs. I

safetyarxiv-cs-ai

PromptPrint: Behavioral Biometrics Through Natural Language Prompting in LLMs

model-releasesarxiv-cs-cl

arXiv:2606.06755v1 Announce Type: new Abstract: Authorship attribution research has traditionally focused on long-form, expressive texts; however, interactions with large language models (LLMs) are ty

Real-Time AttentionBender: Granular Interactive Network Bending of Video Diffusion Transformers

arXiv:2606.06497v1 Announce Type: cross Abstract: Generative video models have achieved remarkable visual fidelity, yet their prompt-only interface offers thin creative agency and obscures the model's

researcharxiv-cs-cv

REMEDI: A Benchmark for Retention and Unlearning Evaluation in Multi-label Clinical Disease Inference

arXiv:2606.07141v1 Announce Type: cross Abstract: Language models trained for clinical disease inference are trained on patient data, which may include sensitive and private information, and data owne

RETROSPECT: RETROsynthesis via Sequential Prediction, and Chemically Transformed-ranking

arXiv:2606.07181v1 Announce Type: cross Abstract: Single-step retrosynthesis needs both accurate first-ranked suggestions and candidate lists that are rich enough for downstream selection. We study th

Hardware

Scalable Joint Resource Allocation for SLO-Constrained LLM Inference in Heterogeneous GPU Clouds

arXiv:2604.07472v2 Announce Type: replace Abstract: Serving large language model (LLM) inference in cloud environments requires jointly optimizing model selection, GPU provisioning, parallelism config

hardwarearxiv-cs-lg

Seeing Without Exposing: Adaptive Privacy Control for Open-World, Context-Hungry MLLMs

arXiv:2606.07175v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) have raised new privacy challenges. On the data side, user-provided inputs often include unpredictable sensitiv

SigmaScale: LLM Compression with SVD-based Low-Rank Decomposition and Learned Scaling Matrices

model-releasesarxiv-cs-cl

arXiv:2606.07098v1 Announce Type: new Abstract: We present SigmaScale, a method for learning auxiliary scaling matrices S to aid truncated Singular Value Decomposition (SVD) based Large Language Model

STREAM: Stochastic Riemannian Flow Matching with Anisotropic Decoder for Digital Histopathology Image Generation

arXiv:2606.07036v1 Announce Type: cross Abstract: Synthetic histopathology image generation addresses critical challenges in computational pathology, including patient privacy and the growing need for

TEVI: Text-Conditioned Editing of Visual Representations via Sparse Autoencoders for Improved Vision-Language Alignment

arXiv:2606.07451v1 Announce Type: cross Abstract: Vision-language models such as CLIP are highly useful for diverse tasks due to their shared image-text embedding space. Despite this, the image and te

VeriDrive: Verifiable Counterfactual Supervision for Cost-Efficient Vision-Language Planning

arXiv:2606.07338v1 Announce Type: new Abstract: Vision-language driving models increasingly use reasoning supervision to bridge perception, prediction, and planning, but existing driving rationales ar

When Recovery Matters: The Blind Spot of Surrogate Privacy in MLLM Editing

arXiv:2606.07171v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) enable flexible instruction-driven image editing, but privacy risks arise when user images expose diverse and u

Beyond Output Matching: Preserving Internal Geometry in NVFP4 LLM Distillatio

arXiv:2606.05682v1 Announce Type: new Abstract: Demand for low-precision inference, including NVFP4-based approaches, has grown as large language models are increasingly deployed in latency and cost c

Evaluating Agentic Configuration Repair for Computer Networks

arXiv:2606.06212v1 Announce Type: new Abstract: Misconfigurations in computer networks remain a major source of critical Internet outages. Research is turning to Large Language Models (LLMs) to automa

Geographic Bias and Diversity in AI Evaluation

arXiv:2606.05187v1 Announce Type: cross Abstract: Among the many challenges hindering the responsible development and deployment of AI, arguably none has faced more intense scrutiny than bias in its v

GuardNet: Ensemble Strategies of Shallow Neural Networks for Robust Prompt Injection and Jailbreak Detection

arXiv:2606.05566v1 Announce Type: new Abstract: Large Language Models (LLMs) have transformed natural language processing, but they remain vulnerable to Prompt Injection (PI) and Jailbreak (JB) attack

Multilingual Fine-Tuning via Localized Gradient Conflict Resolution

arXiv:2606.05613v1 Announce Type: new Abstract: The rapid evolution of Large Language Models (LLMs) has established cross-lingual versatility as a defining feature of modern systems. However, fine-tun

Representation Learning Enables Scalable Multitask Deep Reinforcement Learning

arXiv:2606.05555v1 Announce Type: cross Abstract: Scaling reinforcement learning (RL) to diverse multitask settings remains a central challenge. While recent advances in model-based RL achieve strong

researcharxiv-cs-ai

SentinelBench: A Benchmark for Long-Running Monitoring Agents

arXiv:2606.05342v1 Announce Type: new Abstract: AI agents are increasingly asked to carry out work that spans minutes, hours, or longer. Yet the default model of agent behavior is continuous action: i

Subspace-Aware Sparse Autoencoders for Effective Mechanistic Interpretability

arXiv:2606.06333v1 Announce Type: cross Abstract: Sparse Autoencoders (SAEs) are widely used for mechanistic interpretability in large language models, yet their formulation assigns each latent featur