Membership Inference Attacks for Unseen Classes
arXiv:2506.06488v3 Announce Type: replace-cross Abstract: A key tool in developing safe AI models is emph{data auditing}, i.e., using statistical tools to determine whether harmful content may…
Papers 5629 stories
Simulating Eutopia: Revisiting Long-term Fairness with Outcomes, Performativity, and Dynamics
arXiv:2607.19389v1 Announce Type: cross Abstract: As AI-driven Decision Makers (ADMs) influence our socioeconomic reality, their roles in both enhancing efficiency and amplifying the social biases have…
Generalizable VLA Finetuning via Representation Anchoring and Language-Action Alignment
Finetuning a pretrained vision-language model (VLM) on robot demonstrations via behavior cloning (BC) has become the standard recipe for vision-language-action (VLA) policies. However, BC finetuning progressively…
Beyond Relevance-Centric Retrieval: Rubric-Oriented Document Set Selection and Ranking
As large language models and AI agents become the primary consumers of search results, document set quality determines the upper bound of downstream generation. Yet existing…
SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD
Full-parameter post-training of trillion-parameter-scale MoE models introduces substantial system-level challenges for large-scale distributed training, including severe memory pressure, non-overlapped communication overhead, and inefficient kernel execution. While…
SLPO: Scaling Latent Reasoning via a Surrogate Policy
Reinforcement learning with verifiable rewards has become the predominant recipe for eliciting test-time scaling in explicit Chain-of-Thought reasoners. Yet this scaling path remains computationally costly, since…
G-MAD: A Game-Based Data Generation Framework for Multi-View RGB-T Aerial Object Detection
This work introduces G-MAD, an open-source framework that uses Arma3 to generate synchronized multi-view RGB-T data for aerial object detection. G-MAD addresses key limitations of real-world…
SeededGrasp: Language-Guided Grasping in Complex Scenes with Multiple Embodiments
Practical robotic grasping in complex scenes requires both 3D spatial reasoning and alignment with task-specific requirements. Vision-language models (VLMs) offer a natural way to specify these…
ATSplat: Compact Feed-forward 3D Gaussian Splatting with Adaptive Token Expansion
3D Gaussian Splatting (3DGS) achieves high-quality novel-view synthesis by optimizing freely placed primitives in 3D and adaptively densifying them in under-reconstructed regions. However, this scene-adaptive capacity…
Reading and Steering Representations of Materials-Science Mechanisms in an Open-Weight Language Model
Large language models can answer scientific questions, yet a correct output does not reveal whether the model represents or uses the governing physics. Here we show…
AutoIndex: Learning Representation Programs for Retrieval
We present AutoIndex, a framework for learning representation programs: executable transformations that map raw documents into the representations exposed to a retrieval system. Rather than tuning…
Subliminal Clocks: Latent Time Modelling in Diffusion Language Models
Diffusion Language Models (DLMs) have recently emerged as a promising alternative to autoregressive models. Unlike standard diffusion-based approaches, DLMs are not explicitly conditioned on a timestep,…
Transcription Policy as a Latent Variable: Activating Controllable Verbatim ASR with Word-Level Timing
Modern ASR models trained on heterogeneously annotated data treat transcription style (verbatim vs. intended) as an uncontrolled latent variable, causing measurable decoding instability, evaluation confounding (up…
Computational Humor with Multimodal LLMs: Methods, Datasets, Evaluation, and Challenges
Multimodal humor in memes, cartoons, and comics remains difficult for AI systems because intended meaning depends on non-literal mechanisms, shared cultural knowledge, and communicative intent rather…
Delineate Anything v2: A Global Foundation Model for Field Delineation
Accurate agricultural field boundary delineation at large scale is a foundational task for food security, supply chain transparency, and carbon accounting. While vision foundation models like…
Where Should Optimizer State Live? Tiered State Allocation for Memory-Efficient Mixture-of-Experts Training
Optimizer state is the largest single line item in the memory budget of mixture-of-experts (MoE) training: on a 6.78B-parameter MoE language model, AdamW keeps 50.6 GB…
EduPanel: A Three-Agent LLM Judge for Teaching Videos — Reliability, Complementarity, and Human Trust Calibration
Teaching videos are becoming a major medium for education, creating a growing need for scalable evaluation of their pedagogical quality. Existing automatic judges do not fully…
Generative World Renderer at the Speed of Play
Generative world renderer AlayaRenderer receives structured world states exported from physics engines and synthesizes RGB frames. Unlike models that generate frames from text/control-hints prompts, AlayaRenderer preserves…
AgentDebugX: An Open-Source Toolkit for Failure Observability, Attribution, and Recovery in LLM Agents
LLM agent failures are difficult to debug because the step where an error surfaces is often not the one that caused it. Existing observability tools replay…
Text Template Tokens Are Implicit Semantic Registers in Diffusion Transformers
Text-to-image diffusion transformers (DiTs) jointly process text and image tokens, yet their internal computation during denoising remains poorly understood. We introduce a causal interpretability framework for…
ISO: An RLVR-Native Optimization Stack
Reinforcement learning with verifiable rewards (RLVR) is rapidly advancing the reasoning capabilities of language models, yet the optimization layer that converts reward feedback into weight-space updates…
ABot-World-0: Infinite Interactive World Rollout on a Single Desktop GPU
We present ABot-World-0, an action-conditioned video world model for real-time, long-horizon closed-loop interaction, supported by a multi-source data infrastructure spanning AAA games, simulation engines, and internet…
Trajectory-aware Cross-view Geo-localization with Sequential Observations
Cross-view geo-localization matches ground-level observations against geo-tagged satellite imagery. Recent methods show that sequential queries such as video clips yield richer spatiotemporal cues than single images,…
HPD-Parsing: Hierarchical Parallel Document Parsing
Efficient teamwork typically combines global coordination with parallel execution, a principle not yet fully reflected in unified Vision-Language Model (VLM)-based document parsers. Existing unified parsers process…