AdaHOP: Fast and Accurate Low-Precision Training via Outlier-Pattern-Aware Rotation
arXiv:2604.02525v1 Announce Type: new Abstract: Low-precision training (LPT) commonly employs Hadamard transforms to suppress outliers and mitigate quantization error in large language models (LLMs). However, prior methods apply a fixed transform uniformly, despite substantial variation in outlier structures across tensors....
Internalized Reasoning for Long-Context Visual Document Understanding
arXiv:2604.02371v1 Announce Type: cross Abstract: Visual long-document understanding is critical for enterprise, legal, and scientific applications, yet the best performing open recipes have not explored reasoning, a capability which has driven leaps in math and code performance. We introduce a...
Matrix Profile for Time-Series Anomaly Detection: A Reproducible Open-Source Benchmark on TSB-AD
arXiv:2604.02445v1 Announce Type: new Abstract: Matrix Profile (MP) methods are an interpretable and scalable family of distance-based methods for time-series anomaly detection, but strong benchmark performance still depends on design choices beyond a vanilla nearest-neighbor profile. This technical report documents...
Detecting and Correcting Reference Hallucinations in Commercial LLMs and Deep Research Agents
arXiv:2604.03173v1 Announce Type: new Abstract: Large language models and deep research agents supply citation URLs to support their claims, yet the reliability of these citations has not been systematically measured. We address six research questions about citation URL validity using...
VoxelCodeBench: Benchmarking 3D World Modeling Through Code Generation
arXiv:2604.02580v1 Announce Type: new Abstract: Evaluating code generation models for 3D spatial reasoning requires executing generated code in realistic environments and assessing outputs beyond surface-level correctness. We introduce a platform VoxelCode, for analyzing code generation capabilities for 3D understanding and...
GRADE: Probing Knowledge Gaps in LLMs through Gradient Subspace Dynamics
arXiv:2604.02830v1 Announce Type: new Abstract: Detecting whether a model's internal knowledge is sufficient to correctly answer a given question is a fundamental challenge in deploying responsible LLMs. In addition to verbalising the confidence by LLM self-report, more recent methods explore...
Beyond Precision: Importance-Aware Recall for Factuality Evaluation in Long-Form LLM Generation
arXiv:2604.03141v1 Announce Type: new Abstract: Evaluating the factuality of long-form output generated by large language models (LLMs) remains challenging, particularly when responses are open-ended and contain many fine-grained factual statements. Existing evaluation methods primarily focus on precision: they decompose a...
AXELRAM: Quantize Once, Never Dequantize
arXiv:2604.02638v1 Announce Type: new Abstract: We propose AXELRAM, a smart SRAM macro architecture that computes attention scores directly from quantized KV cache indices without dequantization. The key enabler is a design-time fixed codebook: orthogonal-transform-based quantization concentrates each coordinate's distribution to...
From Broad Exploration to Stable Synthesis: Entropy-Guided Optimization for Autoregressive Image Generation
arXiv:2604.02355v1 Announce Type: new Abstract: Combining Chain-of-Thought (CoT) with Reinforcement Learning (RL) improves text-to-image (T2I) generation, yet the underlying interaction between CoT's exploration and RL's optimization remains unclear. We present a systematic entropy-based analysis that yields three key insights: (1)...
Council Mode: Mitigating Hallucination and Bias in LLMs via Multi-Agent Consensus
arXiv:2604.02923v1 Announce Type: new Abstract: Large Language Models (LLMs), particularly those employing Mixture-of-Experts (MoE) architectures, have achieved remarkable capabilities across diverse natural language processing tasks. However, these models frequently suffer from hallucinations -- generating plausible but factually incorrect content --...
Product-Stability: Provable Convergence for Gradient Descent on the Edge of Stability
arXiv:2604.02653v1 Announce Type: new Abstract: Empirically, modern deep learning training often occurs at the Edge of Stability (EoS), where the sharpness of the loss exceeds the threshold below which classical convergence analysis applies. Despite recent progress, existing theoretical explanations of...
Multi-Turn Reinforcement Learning for Tool-Calling Agents with Iterative Reward Calibration
arXiv:2604.02869v1 Announce Type: new Abstract: Training tool-calling agents with reinforcement learning on multi-turn tasks remains challenging due to sparse outcome rewards and difficult credit assignment across conversation turns. We present the first application of MT-GRPO (Multi-Turn Group Relative Policy Optimization)...
AutoVerifier: An Agentic Automated Verification Framework Using Large Language Models
arXiv:2604.02617v1 Announce Type: new Abstract: Scientific and Technical Intelligence (S&TI) analysis requires verifying complex technical claims across rapidly growing literature, where existing approaches fail to bridge the verification gap between surface-level accuracy and deeper methodological validity. We present AutoVerifier, an...
ESL-Bench: An Event-Driven Synthetic Longitudinal Benchmark for Health Agents
arXiv:2604.02834v1 Announce Type: new Abstract: Longitudinal health agents must reason across multi-source trajectories that combine continuous device streams, sparse clinical exams, and episodic life events - yet evaluating them is hard: real-world data cannot be released at scale, and temporally...
Open, Reliable, and Collective: A Community-Driven Framework for Tool-Using AI Agents
arXiv:2604.00137v1 Announce Type: new Abstract: Tool-integrated LLMs can retrieve, compute, and take real-world actions via external tools, but reliability remains a key bottleneck. We argue that failures stem from both tool-use accuracy (how well an agent invokes a tool) and...
Expert-Choice Routing Enables Adaptive Computation in Diffusion Language Models
arXiv:2604.01622v1 Announce Type: new Abstract: Diffusion language models (DLMs) enable parallel, non-autoregressive text generation, yet existing DLM mixture-of-experts (MoE) models inherit token-choice (TC) routing from autoregressive systems, leading to load imbalance and rigid computation allocation. We show that expert-choice (EC)...
Eyla: Toward an Identity-Anchored LLM Architecture with Integrated Biological Priors -- Vision, Implementation Attempt, and Lessons from AI-Assisted Development
arXiv:2604.00009v1 Announce Type: cross Abstract: We present the design rationale, implementation attempt, and failure analysis of Eyla, a proposed identity-anchored LLM architecture that integrates biologically-inspired subsystems -- including HiPPO-initialized state-space models, zero-initialized adapters, episodic memory retrieval, and calibrated uncertainty training...
Detecting Complex Money Laundering Patterns with Incremental and Distributed Graph Modeling
arXiv:2604.01315v1 Announce Type: new Abstract: Money launderers take advantage of limitations in existing detection approaches by hiding their financial footprints in a deceitful manner. They manage this by replicating transaction patterns that the monitoring systems cannot easily distinguish. As a...
Did Nazis escape on a UFO? Dev who asked the question just built the official White House app.
Did you know that Ohio is a hotbed of UFO activity?
Locally Confident, Globally Stuck: The Quality-Exploration Dilemma in Diffusion Language Models
arXiv:2604.00375v1 Announce Type: new Abstract: Diffusion large language models (dLLMs) theoretically permit token decoding in arbitrary order, a flexibility that could enable richer exploration of reasoning paths than autoregressive (AR) LLMs. In practice, however, random-order decoding often hurts generation quality....
Microsoft takes on AI rivals with three new foundational models
MAI released models that can transcribe voice into text as well as generate audio and images after the group's formation six months ago.
The Chronicles of RiDiC: Generating Datasets with Controlled Popularity Distribution for Long-form Factuality Evaluation
arXiv:2604.00019v1 Announce Type: cross Abstract: We present a configurable pipeline for generating multilingual sets of entities with specified characteristics, such as domain, geographical location and popularity, using data from Wikipedia and Wikidata. These datasets are intended for evaluating the factuality...
Adversarial Moral Stress Testing of Large Language Models
arXiv:2604.01108v1 Announce Type: new Abstract: Evaluating the ethical robustness of large language models (LLMs) deployed in software systems remains challenging, particularly under sustained adversarial user interaction. Existing safety benchmarks typically rely on single-round evaluations and aggregate metrics, such as toxicity...
FourierMoE: Fourier Mixture-of-Experts Adaptation of Large Language Models
arXiv:2604.01762v1 Announce Type: new Abstract: Parameter-efficient fine-tuning (PEFT) has emerged as a crucial paradigm for adapting large language models (LLMs) under constrained computational budgets. However, standard PEFT methods often struggle in multi-task fine-tuning settings, where diverse optimization objectives induce task...
Learning ECG Image Representations via Dual Physiological-Aware Alignments
arXiv:2604.01526v1 Announce Type: new Abstract: Electrocardiograms (ECGs) are among the most widely used diagnostic tools for cardiovascular diseases, and a large amount of ECG data worldwide appears only in image form. However, most existing automated ECG analysis methods rely on...
AI Company Safety Practices Fall Short of Public Commitments and Show Structural Weaknesses, as Top Performers Widen the Gap
But in a win for transparency, five leading companies participated in the scorecard's survey for the first time, providing critical new information to the public.
Google DeepMind Falls Behind OpenAI in Latest Safety Review; All AI Companies Still Falling Short, Say Experts
The Future of Life Institute’s 2025 summer update to its AI Safety Index shows some companies making incremental progress, but dangerous gaps remain in key categories such as risk assessment and controlling the systems they plan to build.
ByteDance’s new AI video generation model, Dreamina Seedance 2.0, comes to CapCut
The new model in CapCut will have built-in protections for making video from real faces or unauthorized intellectual property.
Mistral releases a new open source model for speech generation
The model, which lets enterprises build voice agents for sales and customer engagement, puts Mistral in direct competition with the likes of ElevenLabs, Deepgram, and OpenAI.
Boston University websites are currently unavailable.