11
TAG: A Lightweight Framework for Test-Driven Agentic Artifact Generation
The paper introduces TAG, a lightweight framework designed to improve the reliability of LLM-generated structured artifacts through rigorous, test-driven validation.
11
Behavior Foundations for Quadruped Robots: ABot-C0 Technical Report
The ABot-C0 technical report details a new framework for quadrupedal robot control designed to overcome the scarcity of animal motion-capture data.
11
Echoes: A semantically-aligned music deepfake detection dataset
The Echoes dataset provides over 130 hours of audio across multiple genres to benchmark and train robust music deepfake detection systems.
11
ParamMute: Suppressing Knowledge-Critical FFNs for Faithful Retrieval-Augmented Generation
Researchers have introduced ParamMute, a method that improves the faithfulness of retrieval-augmented generation by suppressing knowledge-critical feed-forward networks that cause models to ignore retrieved context.
11
Persuasion Attacks Can Decrease Effectiveness of CoT Monitoring
Researchers have found that persuasion-based jailbreak attacks can undermine the effectiveness of chain-of-thought monitoring in detecting misaligned AI behavior.
11
V-VLAPS: Value-Guided Planning for Vision-Language-Action Models
The V-VLAPS framework integrates value-guided planning with vision-language-action models to improve robotic manipulation performance under distribution shifts and long-horizon tasks.
11
Retrieval-Augmented Generation Must Move Beyond Factual Grounding to Represent Diverse Opinions
This position paper argues that current retrieval-augmented generation systems are overly focused on factual grounding and fail to adequately represent diverse opinions.
11
VocaDet: Sample-Driven Open-Vocabulary Object Detection and Segmentation via Visual Tokenization and Vector Database Retrieval
VocaDet is a new open-vocabulary object detection and segmentation framework that scales to large object categories using visual tokenization and vector database retrieval.
11
TRACE: A Two-Channel Robust Attribution Watermark via Complementary Embeddings for LLM-Agent Trajectories
Researchers developed TRACE, a robust watermarking method designed to protect and verify the attribution of LLM agent trajectory logs against unauthorized rebranding or model substitution.
11
GitLake: Git-for-data for the agentic lakehouse
GitLake introduces a version-control system for data lakehouses that allows autonomous AI agents to work on isolated branches before merging changes.
10
苹果股票获得罕见的看跌评级，KeyBanc表示需求和估值令人担心
KeyBanc Capital Markets downgraded Apple's stock rating to underweight, citing concerns over demand and high valuation relative to historical averages.
10
Chasing the 2030 Power Generation Target: China's Artificial Sun Race Heats Up
Driven by the massive energy demands of artificial intelligence, China's private nuclear fusion sector is accelerating development toward a 2030 power generation goal.
10
Reaction-network reasoning with frontier models for experimentally confirmed catalyst-selectivity hypotheses
The study demonstrates how frontier AI models can be used to reason through reaction networks and generate experimentally validated hypotheses for catalyst selectivity.
10
The Illusion of Equivalency: Statistical Characterization of Quantization Effects in LLMs
A new study proposes a decision-level metric called correctness agreement to better capture the behavioral changes in large language models caused by post-training quantization.
10
Multimodal Unlearning Across Vision, Language, Video, and Audio: Survey of Methods, Datasets, and Benchmarks
This paper provides a comprehensive survey of methods, datasets, and benchmarks for multimodal machine unlearning across various data modalities.
10
DreamCharacter-1: From 3D Generative Foundation Models to Product-Ready Character Generation
DreamCharacter-1 is a post-adaptation framework designed to refine pretrained 3D foundation models for high-fidelity, production-ready character generation.
10
Nvidia is a victim of the compute marketplace it created
An analysis suggests Nvidia faces intense competition and market pressures as a direct result of popularizing the high-value AI compute market.
10
KVpop -- Key-Value Cache Compression with Predictive Online Pruning
Researchers introduced KVpop, a method that compresses key-value caches in autoregressive decoding by learning a fixed-budget eviction policy through direct supervision.
10
A Stochastic--Geometric Theory of Scaling Laws in Grokking
This study provides a theoretical characterization of the mechanisms behind delayed generalization, or grokking, in neural networks using a stochastic-geometric framework.
10
Different Teachers, Different Capabilities: Sub-1B On-Device Distillation for Structured Text Enrichment
Researchers evaluated the effectiveness of distilling structured text extraction capabilities from an 8-billion parameter reasoning model into a sub-1-billion parameter on-device model.
10
A First-Principles Theory of Slow Thinking and Active Perception
This paper provides a mathematical formulation of slow thinking and active perception to guide the design and training of reasoning-focused language models.
10
Predicting Scale-Up of Metal-Organic Framework Syntheses with Large Language Models
Researchers developed ScaleMOF, a dataset and fine-tuning strategy that enables large language models to predict and prioritize viable candidates for scaling up metal-organic framework syntheses.
10
PhasorFlow: A Python Library for Unit Circle Based Computing
PhasorFlow is a new open-source Python library designed to facilitate complex-valued computations on the unit circle manifold.
10
Theoria: Rewrite-Acceptability Verification over Informal Reasoning States
Researchers have developed Theoria, a verification architecture that audits large language model outputs by rewriting solutions into typed state transitions to ensure correctness.