Qi Li

The paper introduces SURE, a unified framework designed to standardize and improve the comparability and reproducibility of evaluations for advanced speech understanding models.

The paper introduces I-WebGenBench, a framework and benchmark that converts static scientific papers into executable, interactive web systems, allowing users to dynamically explore the paper's mechanisms.

The paper demonstrates that specialized coding agents, using only text and image access within a sandbox, can effectively solve complex omnimodal tasks, often outperforming state-of-the-art native omnimodal models.

The paper introduces AdvCL, a framework that repurposes adversarial perturbations as a geometric control signal to stabilize continual learning in large language models, significantly reducing forgetting and enhancing robustness.

The paper proposes Self-Adaptive Monotonic Normalization (SAMN), a hyperparameter-friendly method that improves long-tailed recognition by enforcing monotonicity on per-class weight norms without requiring parameter regularization.

The paper introduces AutoMedBench, a novel workflow-aware benchmark that evaluates autonomous medical-AI agents across a five-stage research process, revealing that agents struggle most with validation and submission.

TempoVLA is a novel Vision-Language-Action model that enables controllable execution speed for robot manipulation by explicitly conditioning the policy on the desired speed.

The paper introduces RedEdit, an agentic red-teaming framework that demonstrates that malicious images can be easily edited to bypass safety classifiers while retaining their harmful semantics.

Introduces Looped World Models, a looped architecture for world modelling that iteratively refines latent environment states for up to 100x parameter efficiency.

This paper studies the behavior of mixture-of-experts (MoE) models under distribution shift and proposes an adversarial reweighting method to improve their calibration.

This paper proposes a two-stage training framework to pretrain action modules with motion priors before Vision-Language-Action (VLA) alignment, improving VLA performance and reducing optimization challenges.

This paper proposes GLAN, a sequence modeling framework for Personalized Landing Page Modeling on online platforms, addressing the limitations of previous reinforcement learning approaches.

This paper proposes ShopX, a model-centric framework for intent-driven shopping experiences using a single foundation model for intent understanding, execution planning, and item-space operations.

The paper presents SABLE, an NDA-safe framework that allows large language models to optimize analog circuits in industrial EDA tools while protecting proprietary information.

This paper introduces LingBot-Video, a video pretraining paradigm for embodied intelligence using a DiT-based approach, Mixture-of-Experts framework, and extensive robot-oriented data.

This paper introduces LingBot-VA 2.0, a video-action foundation model designed for embodiment, with semantic visual-action tokenization, causal pretraining, sparse MoE backbone, and enhanced asynchronous inference.

This paper introduces BadWAM, a framework for modeling and evaluating World-Action Drift Attacks, a new class of adversarial attacks that break the alignment between a World-Action Model's (WAM's) imagined future and its executed actions.

This paper presents a practical pipeline for designing and deploying large-scale Mixed Reality art exhibitions using SLAM-based alignment, and evaluates its impact on technical stability and user experience.

This paper introduces a training recipe for sentence-level and long-form streaming speech-to-speech translation using only 2k hours of paired cross-lingual data and auxiliary supervision.

The paper presents CHASE, an application-driven framework that explores physically feasible Cross-layer Heterogeneous System architectures for executing workloads with diverse requirements.