Paper Archive

Soumik Mukhopadhyay, Prateksha Udhayanan, Abhinav Shrivastava 3/9/2026 arxiv

Diffusion models degrade images through noise, and reversing this process reveals an information hierarchy across timesteps. Scale-space theory exhibits a similar hierarchy via low-pass filtering. We formalize this connection and show that highly noisy diffusion states contain no more information th...

Weize Liu, Minghui Liu, Sy-Tuyen Ho, Souradip Chakraborty, Xiyao Wang, Furong Huang 3/9/2026 arxiv

Training large language models (LLMs) as autonomous agents often begins with imitation learning, but it only teaches agents what to do without understanding why: agents never contrast successful actions against suboptimal alternatives and thus lack awareness of action quality. Recent approaches atte...

Akshay Gulati, Kanha Singhania, Tushar Banga, Parth Arora, Anshul Verma, Vaibhav Kumar Singh, Agyapal Digra, Jayant Singh Bisht, Danish Sharma, Varun Singla, Shubh Garg 3/9/2026 arxiv

Large language models are increasingly used for financial analysis and investment research, yet systematic evaluation of their financial reasoning capabilities remains limited. In this work, we introduce the AI Financial Intelligence Benchmark (AFIB), a multi-dimensional evaluation framework designe...

Kai Zou, Dian Zheng, Hongbo Liu, Tiankai Hang, Bin Liu, Nenghai Yu 3/9/2026 arxiv

Autoregressive (AR) diffusion offers a promising framework for generating videos of theoretically infinite length. However, a major challenge is maintaining temporal continuity while preventing the progressive quality degradation caused by error accumulation. To ensure continuity, existing methods t...

Anas ALsobeh, Raneem Alkurdi 3/9/2026 arxiv

The rapid advancement of artificial intelligence (AI) technologies presents both unprecedented opportunities and significant challenges for sustainable economic development. While AI offers transformative potential for addressing environmental challenges and enhancing economic resilience, its deploy...

Phillip Long, Zachary Novack, Chris Donahue 3/9/2026 arxiv

Autoregressive "language" models (LMs) trained on raw waveforms can be repurposed for lossless audio compression, but prior work is limited to 8-bit audio, leaving open whether such approaches work for practical settings (16/24-bit) and can compete with existing codecs. We benchmark LM-based compres...

Nanjun Li, Pinqi Cheng, Zean Liu, Minghe Tian, Xuanyin Wang 3/9/2026 arxiv

Single-stage multi-person pose estimation aims to jointly perform human localization and keypoint prediction within a unified framework, offering advantages in inference efficiency and architectural simplicity. Consequently, multi-scale real-time detection architectures, such as YOLO-like models, ar...

Yang Cai, Vineet Gupta, Zun Li, Aranyak Mehta 3/9/2026 arxiv

The celebrated Myerson--Satterthwaite theorem shows that in bilateral trade, no mechanism can be simultaneously fully efficient, Bayesian incentive compatible (BIC), and budget balanced (BB). This naturally raises the question of how closely the gains from trade (GFT) achievable by a BIC and BB mech...

Mengyi Shan, Shouchieh Chang, Ziqian Bai, Shichen Liu, Yinda Zhang, Luchuan Song, Rohit Pandey, Sean Fanello, Zeng Huang 3/9/2026 arxiv

We tackle the challenging task of generating complete 3D facial animations for two interacting, co-located participants from a mixed audio stream. While existing methods often produce disembodied "talking heads" akin to a video conference call, our work is the first to explicitly model the dynamic 3...

Siqi Shang, Minchao Huang, Bill Fan, Lillian Chin 3/9/2026 arxiv

Accurate pre-contact grasp force selection is critical for safe and reliable robotic manipulation. Adaptive controllers regulate force after contact but still require a reasonable initial estimate. Starting a grasp with too little force requires reactive adjustment, while starting a grasp with too h...