Every story we have kept, newest first.
Looking for the daily editions? → Past editions
Page 1368 of 1372
LiveMedBench offers weekly updated real-world clinical cases for LLM evaluation, avoiding contamination via temporal separation. Multi-agent curation ensures integrity; automated rubric evaluation aligns with experts better than alternatives.
ArXiv AI · 215d ago
Early Moltbook data from 6k agents shows power-law participation and small-world connectivity like human networks. Micro patterns are alien: shallow threads, low reciprocity, 34% duplicate templates.
ArXiv AI · 215d ago
Introduces diffusion-based generative priors in DGP framework for reconstructing CT images from sparse-view sinograms. Combines iterative optimization with neural generative power while preserving explainability.
ArXiv AI · 215d ago
DiffGDA uses diffusion and SDEs to model continuous structure-semantic evolution from source to target graphs. A domain-aware network guides trajectories to optimal adaptation paths.
ArXiv AI · 215d ago
DermFM-Zero is a vision-language model trained on 4M multimodal data for zero-shot dermatology tasks. Achieves SOTA on benchmarks and outperforms clinicians in studies.
ArXiv AI · 215d ago
CycFlow replaces diffusion generation with deterministic point transport for combinatorial optimization like TSP. It learns vector fields to map coordinates to circular arrangements for angular sorting.
ArXiv AI · 215d ago
Proposes authenticated prompts and context for cryptographic provenance in LLM apps. Features policy algebra with Byzantine resistance and layered defenses.
ArXiv AI · 215d ago
Proposes CrossTALK for red-teaming VLMs via cross-modal entanglement attacks. Extends clues across modalities with scalable complexity.
ArXiv AI · 215d ago
CRL uses reinforcement learning to select sparse autoencoder (SAE) features for steering language models at each token, revealing which features impact outputs. It includes adaptive masking for diverse features and enables analysis like branch point tracking and layer-wise comparisons.
ArXiv AI · 215d ago
Foundation models match task-specific discrimination in abdominal trauma CT but suffer specificity drops from negative-class heterogeneity like solid organ injuries. Task-specific models handle confounds better.
ArXiv AI · 215d ago
CLI-Gym generates 1,655 CLI tasks via agentic environment inversion from Dockerfiles. It simulates histories to create buggy states and derives tasks with error messages.
ArXiv AI · 215d ago
C^2ROPE enhances Rotary Position Embedding for 3D Large Multimodal Models by addressing spatial locality loss and long-term attention decay. It introduces spatio-temporal continuous positional embeddings using triplet hybrid indices and Chebyshev Causal Masking.
ArXiv AI · 215d ago
BNRM introduces Bayesian non-negative reward modeling to combat reward hacking in RLHF. It uses sparse latent factors for disentangled, debiased rewards.
ArXiv AI · 215d ago
Introduces Blockwise Advantage Estimation for GRPO in structured generations, assigning per-objective advantages to avoid interference. Uses Outcome-Conditioned Baseline to estimate advantages without nested rollouts.
ArXiv AI · 215d ago
Multi-dimensional zero-shot benchmark evaluates four TSFMs (Chronos, Moirai, TinyTimeMixer) vs. baselines on ERCOT data.
ArXiv AI · 215d ago
EvoCodeBench evaluates LLM-driven coding systems on self-evolution, efficiency, and human-comparable performance across languages. Tracks dynamics like solving time and improvements over iterations.
ArXiv AI · 215d ago
Proposes causal reward shaping from offline data for continuous RL under confounders. Derives tight value bounds via causal Bellman equation for PBRS.
ArXiv AI · 215d ago
Introduces authenticated workflows as a complete trust layer for enterprise agentic AI, protecting prompts, tools, data, and context. Enforces intent and integrity via cryptography and MAPL policy language.
ArXiv AI · 215d ago
AugVLA-3D integrates depth estimation from RGB inputs via VGGT to enrich 3D features in vision-language-action models. An action assistant module ensures consistency with control tasks.
ArXiv AI · 215d ago
AudioRouter applies RL to teach large audio language models (LALMs) when to use external audio tools, improving fine-grained perception without heavy training. It optimizes a lightweight routing policy while freezing the base model.
ArXiv AI · 215d ago
Aletheia is a math research agent that generates, verifies, and revises solutions using advanced Gemini Deep Think. It achieves milestones like fully AI-generated papers, human-AI collaborations, and solving four open Erdos problems.
ArXiv AI · 215d ago
AI-PACE synthesizes literature to propose a framework for integrating AI into medical education across the learning continuum. It identifies key competencies, curricular approaches, and strategies emphasizing longitudinal integration and interdisciplinary collaboration.
ArXiv AI · 215d ago
Frontier AI models excel in advanced math but consistently fail at multi-digit integer addition. Errors primarily stem from operand misalignment or carry failures, explaining most mistakes in top models like Claude, GPT, and Gemini.
ArXiv AI · 215d ago
AgentTrace instruments LLM agents for structured logging across operational, cognitive, and contextual traces. Provides runtime transparency for security and monitoring in high-stakes settings.
ArXiv AI · 215d ago
Proves LLMs possess predictive partial-world models via task-agnostic affordances for intents. Introduces distribution-robust affordances for multi-task efficiency.
ArXiv AI · 215d ago
AD² analyzes vulnerabilities in end-to-end driving agents like Transfuser to physics, EMI, and digital attacks in CARLA. Driving scores drop up to 99% under threats.
ArXiv AI · 215d ago
Lightweight adapters trained on interpretability artifacts enable reliable self-interpretation in frozen LMs. A simple scalar affine adapter outperforms baselines in feature labeling, topic identification, and implicit reasoning decoding.
ArXiv AI · 215d ago
ADAlign tackles graph domain adaptation by adaptively aligning discrepancies via Neural Spectral Discrepancy (NSD). Uses neural characteristic functions and minimax sampling without heuristics.
ArXiv AI · 215d ago
CoLin introduces a 1% parameter low-rank complex adapter for vision foundation models. It resolves convergence issues in composite matrices with tailored loss.
ArXiv AI · 215d ago
The article questions whether Apple's AI-upgraded Siri will launch before CEO Tim Cook retires. It emphasizes that while delays are tolerable, outright failure is unacceptable.
Ifanr (爱范儿) · 215d ago