arXiv:2603.00523v2 Announce Type: replace-cross Abstract: Every mechanistic circuit carries an invisible asterisk: it reflects not just the model’s computation, but the analyst’s choice of pruning threshold. Change that choice and the circuit changes, yet current practice treats a single pruned subgraph as ground truth with no way to distinguish robust structure from threshold artifacts. We […]
Uncertainty-aware Prototype Learning with Variational Inference for Few-shot Point Cloud Segmentation
arXiv:2603.19757v1 Announce Type: cross Abstract: Few-shot 3D semantic segmentation aims to generate accurate semantic masks for query point clouds with only a few annotated support examples. Existing prototype-based methods typically construct compact and deterministic prototypes from the support set to guide query segmentation. However, such rigid representations are unable to capture the intrinsic uncertainty introduced […]
Toward High-Fidelity Visual Reconstruction: From EEG-Based Conditioned Generation to Joint-Modal Guided Rebuilding
arXiv:2603.19667v1 Announce Type: cross Abstract: Human visual reconstruction aims to reconstruct fine-grained visual stimuli based on subject-provided descriptions and corresponding neural signals. As a widely adopted modality, Electroencephalography (EEG) captures rich visual cognition information, encompassing complex spatial relationships and chromatic details within scenes. However, current approaches are deeply coupled with an alignment framework that forces […]
The Phish, The Spam, and The Valid: Generating Feature-Rich Emails for Benchmarking LLMs
arXiv:2511.21448v5 Announce Type: replace-cross Abstract: In this paper, we introduce a metadata-enriched generation framework (PhishFuzzer) that seeds real emails into Large Language Models (LLMs) to produce 23,100 diverse, structurally consistent email variants across controlled entity and length dimensions. Unlike prior corpora, our dataset features strict three-class labels (Phishing, Spam, Valid), provides full URL and attachment […]
On the Structural Non-Preservation of Epistemic Behaviour under Policy Transformation
arXiv:2602.21424v2 Announce Type: replace-cross Abstract: Reinforcement learning (RL) agents under partial observability often condition actions on internally accumulated information such as memory or inferred latent context. We formalise such information-conditioned interaction patterns as behavioural dependency: variation in action selection with respect to internal information under fixed observations. This induces a probe-relative notion of $epsilon$-behavioural equivalence […]
Spectral Alignment in Forward-Backward Representations via Temporal Abstraction
arXiv:2603.20103v1 Announce Type: cross Abstract: Forward-backward (FB) representations provide a powerful framework for learning the successor representation (SR) in continuous spaces by enforcing a low-rank factorization. However, a fundamental spectral mismatch often exists between the high-rank transition dynamics of continuous environments and the low-rank bottleneck of the FB architecture, making accurate low-rank representation learning difficult. […]
The Residual Stream Is All You Need: On the Redundancy of the KV Cache in Transformer Inference
arXiv:2603.19664v1 Announce Type: cross Abstract: The key-value (KV) cache is widely treated as essential state in transformer inference, and a large body of work engineers policies to compress, evict, or approximate its entries. We prove that this state is entirely redundant: keys and values at every layer are deterministic projections of the residual stream, and […]
VideoSeek: Long-Horizon Video Agent with Tool-Guided Seeking
arXiv:2603.20185v1 Announce Type: cross Abstract: Video agentic models have advanced challenging video-language tasks. However, most agentic approaches still heavily rely on greedy parsing over densely sampled video frames, resulting in high computational cost. We present VideoSeek, a long-horizon video agent that leverages video logic flow to actively seek answer-critical evidence instead of exhaustively parsing the […]
Federated Learning Playground
arXiv:2602.19489v2 Announce Type: replace-cross Abstract: We present Federated Learning Playground, an interactive browser-based platform inspired by and extends TensorFlow Playground that teaches core Federated Learning (FL) concepts. Users can experiment with heterogeneous client data distributions, model hyperparameters, and aggregation algorithms directly in the browser without coding or system setup, and observe their effects on client […]
VIRO: Robust and Efficient Neuro-Symbolic Reasoning with Verification for Referring Expression Comprehension
arXiv:2601.12781v2 Announce Type: replace Abstract: Referring Expression Comprehension (REC) aims to localize the image region corresponding to a natural language query. Recent neuro-symbolic REC approaches leverage large language models (LLMs) and vision-language models (VLMs) to perform compositional reasoning, decomposing queries into structured programs and executing them step-by-step. While such approaches achieve interpretable reasoning and strong […]
PolicySim: An LLM-Based Agent Social Simulation Sandbox for Proactive Policy Optimization
arXiv:2603.19649v1 Announce Type: cross Abstract: Social platforms serve as central hubs for information exchange, where user behaviors and platform interventions jointly shape opinions. However, intervention policies like recommendation and content filtering, can unintentionally amplify echo chambers and polarization, posing significant societal risks. Proactively evaluating the impact of such policies is therefore crucial. Existing approaches primarily […]
Pseudo-Simulation for Autonomous Driving
arXiv:2506.04218v3 Announce Type: replace-cross Abstract: Existing evaluation paradigms for Autonomous Vehicles (AVs) face critical limitations. Real-world evaluation is often challenging due to safety concerns and a lack of reproducibility, whereas closed-loop simulation can face insufficient realism or high computational costs. Open-loop evaluation, while being efficient and data-driven, relies on metrics that generally overlook compounding errors. […]