arXiv subjects

Changhao Zhang

Publications and source records attributed to Changhao Zhang.

14 recordsLinked to original sources

arXiv2026

Realtime-Venus: A full-duplex interaction system with asynchronous delegation

Natural interaction in digital and physical environments requires continuous perception and timely responses. Spoken dialogue relies on acoustic and linguistic cues, while video interaction also requires grounding the conversation in evolving visual context. We present Realtime-Venus, a proactive full-duplex interaction system with two separately trained 9B models: Realtime-Venus-Omni for audio-visual interaction and Realtime-Venus-Audio for spoken interaction. Each model serves as a complete conversational frontend, integrating continuous perception, conversational control, and native speech generation through a shared causal timeline for user inputs, model outputs, and delegation events. A dual-loop runtime coordinates live interaction with background reasoning and tool execution. Foreground interaction continues while Realtime-Venus-Harness executes tasks asynchronously and returns results for integration into the ongoing dialogue. Both models follow a common post-training recipe combining offline understanding, proactive full-duplex trajectories, and delegation workflows. Among the evaluated online models, Realtime-Venus-Omni achieves the highest scores on six of eight video benchmarks, including StreamingBench (70.2%), OVO-Bench (64.7%), and Daily-Omni (81.3%). Across eight audio understanding and spoken question answering benchmarks, Realtime-Venus-Audio leads the compared models on MMAU (78.0%), MMAU-Pro (63.2%), Llama Questions (83.8%), and Speech CMMLU (67.8%), while matching the best VoiceBench AlpacaEval score of 4.81. On Full-Duplex-Bench v1.5, Realtime-Venus-Audio responds to 75% of user interruptions and achieves continuation rates of 97%, 88%, and 86% under backchannels, other-directed speech, and background speech, respectively, exceeding Gemini 3.1 Live and GPT-4o on all three continuation metrics.

cs.CV↗

arXiv2026

Tactile-WAM: Touch-Aware World Action Model with Tactile Asymmetric Attention

World Action Models (WAMs) jointly predict future visual observations and actions, but visual futures alone often miss slip, jamming, contact-direction changes, and subtle misalign- ment in contact-rich manipulation. Tactile signals reveal these hidden physical states, yet naive tactile-token injection can disrupt visual dynamics modeling due to the limited scale of tactile data, a phenomenon we term tactile pollution. We in- troduce Tactile-WAM, which uses asymmetric attention to block video queries from tactile keys while preserving tac- tile access for action queries. A contact-change-aware bias further strengthens action attention to touch. Because tactile pixel changes do not reliably reflect contact changes, we derive Observed proxy changes drive the attention bias, while future- proxy supervision preserves action-relevant contact dynamics in predicted tactile representations. On ManiFeel, visual-path isolation reduces deviation from the RGB-only trajectory by 21.8% in MSE at the step-matched 20K checkpoint without a statistically detectable change in ground-truth video qual- ity. The full model improves average success from 15.6% to 32.7%, with VideoClean providing the largest gain. On five real-robot tasks, Tactile-WAM achieves 49.2% success.

cs.RO↗

arXiv2026

RefineRank: Joint Box Refinement and Ranking for Surgical Spatio-Temporal Grounding

Surgical spatio-temporal grounding (STG) requires locating, at each video time specified by a procedural question, the object that the question asks about. Existing approaches face a trade-off: vision language models understand the question context but produce imprecise coordinates, whereas open-set detectors provide localized candidate boxes whose confidence does not reflect which box answers the question. We introduce RefineRank, which closes this gap at the candidate-box level. A compact trainable module, RefineNet, combines the language and regional features of a frozen medical vision language model with the proposals of a frozen open-set detector: it predicts a bounded coordinate correction and a quality score for every candidate box, and a fixed decoding rule returns the original or refined box with the highest score. On the MedVidBench Official Rankings (Verified), RefineRank records 0.421 STG mIoU, the highest displayed STG score, while its global multi-metric rank is 11. In a controlled evaluation on separate training and evaluation videos, coordinate correction raises the candidate oracle upper bound from 0.6772 to 0.7302, and ranking the joint pool of original and refined candidates by their RefineNet scores improves STG mIoU from 0.2719 to 0.4534, whereas separately trained selectors over the same pool reach at most 0.4186. These results show that a small box-level module can reconcile question understanding with precise localization without retraining either backbone. Code is available at [https://github.com/linzhe001/RefineRank](https://github.com/linzhe001/RefineRank).

cs.CV↗

arXiv2026

AT-ADD: A Benchmark and Challenge for Robust and All-Type Audio Deepfake Detection

Recent audio generation models can synthesize high-fidelity speech, environmental sound, singing voice, and music, creating new risks for multimedia trust. Existing audio deepfake detection (ADD) benchmarks remain predominantly speech-centric and often underrepresent realistic channel variation and diverse audio types. This paper presents AT-ADD, a large-scale benchmark and challenge designed to evaluate both robust speech deepfake detection and all-type audio deepfake detection. Track 1 evaluates binary speech detection under unseen generators, diverse recording conditions, signal perturbations, and replay effects. Track 2 evaluates type-agnostic real/fake detection over speech, sound, singing, and music when the audio type is unknown at test time. We detail the dataset construction, evaluation protocol, and reproducible baselines, and analyze the final systems submitted to the ACM Multimedia 2026 Grand Challenge. The strongest official baseline obtains 76.73% and 79.47% Macro-F1 on the Track 1 and Track 2 evaluation sets, respectively, whereas the winning challenge systems reach 90.71% and 96.10%. Beyond aggregate rankings, sample-level analysis of the top five submissions examines generator- and type-level difficulty, cross-system error complementarity, and ranking stability. The results show that large-scale self-supervised representations, condition-aware augmentation, multi-crop inference, and structured fusion or routing are central to generalization, while generator-specific robustness and consistent performance across diverse audio types remain unresolved.

cs.SD↗

arXiv2026

AT-ADD: All-Type Audio Deepfake Detection Challenge Summary

This paper summarizes the ACM Multimedia 2026 AT-ADD Grand Challenge on all-type audio deepfake detection. AT-ADD contains two tracks: robust speech deepfake detection under realistic acoustic and channel variations, and type-agnostic detection over speech, environmental sound, singing voice, and music. We describe the challenge tasks, dataset and evaluation-set design, official leaderboard results, and common design patterns observed in participating systems. The best Track 1 system achieved 90.71% Macro-F1 on the final evaluation set, while the best Track 2 system achieved 96.10% Macro-F1. The final submissions show that strong systems commonly combine large-scale self-supervised audio representations, data augmentation, multi-crop inference, and structured fusion or routing. The results also reveal remaining challenges in generalization to unseen generators, robustness to realistic speech-domain distortions, and balanced performance across heterogeneous audio types.

cs.SD↗

arXiv2026

The MiniMax-M2 Series: Mini Activations Unleashing Max Real-World Intelligence

We introduce the MiniMax-M2 series, a family of Mixture-of-Experts language models built around the principle that mini activations can unleash maximum real-world intelligence. The flagship M2 contains 229.9B total parameters with only 9.8B activated per token. Designed end-to-end for agentic deployment, the M2 series rests on three components: (i) agent-driven data pipelines producing large-scale, verifiable trajectories across agentic coding and agentic cowork, each grounded in an executable workspace and an artifact-aligned reward; (ii) Forge, a scalable agent-native RL system that adapts to long-horizon agent trajectories, paired with windowed-FIFO scheduling, prefix-tree merging, inference optimization, and a clean training-inference-agent decoupling that supports both white-box and black-box agents; (iii) the latest M2.7 checkpoint takes an early step toward self-evolution -- autonomously debugging training runs and modifying its own scaffold. Across M2 through M2.7, this combination translates a mini-activation footprint into frontier-tier performance on agentic coding, deep search, office-task, and reasoning benchmarks.

cs.AI↗

arXiv2026

AuthGlass: Benchmarking Voice Liveness Detection and Authentication on Smart Glasses via Comprehensive Acoustic Features

With the rapid advancement of smart glasses, voice interaction has been widely adopted due to its naturalness and convenience. However, its practical deployment is often undermined by vulnerability to spoofing attacks, while no public dataset currently exists for voice liveness detection and authentication in smart-glasses scenarios. To address this challenge, we first collect a multi-acoustic-modal dataset comprising 16-channel audio data from 42 subjects, along with corresponding attack samples covering two attack categories. Based on insights derived from this collected data, we propose AuthG-Live, a sound-field-based voice liveness detection method, and AuthG-Net, a multi-acoustic-modal authentication model. We further benchmark seven voice liveness detection methods and four authentication methods across diverse acoustic modalities. The results demonstrate that our proposed approach achieves state-of-the-art performance on four benchmark tasks, and extensive ablation studies validate the generalizability of our methods \red{under real-world constraints}. Finally, we release this dataset, termed AuthGlass, to facilitate future research on voice liveness detection and authentication for smart glasses.

cs.HC↗

arXiv2026

GTR-Turbo: Merged Checkpoint is Secretly a Free Teacher for Agentic VLM Training

Multi-turn reinforcement learning (RL) for multi-modal agents built upon vision-language models (VLMs) is hampered by sparse rewards and long-horizon credit assignment. Recent methods densify the reward by querying a teacher that provides step-level feedback, e.g., Guided Thought Reinforcement (GTR) and On-Policy Distillation, but rely on costly, often privileged models as the teacher, limiting practicality and reproducibility. We introduce GTR-Turbo, a highly efficient upgrade to GTR that matches its performance without training on or querying an expensive teacher model. Specifically, GTR-Turbo merges the weights of checkpoints produced during ongoing RL training and then uses the resulting merged model as a "free" teacher to guide subsequent RL via supervised fine-tuning or soft logit distillation. This design removes dependence on privileged VLMs (e.g., GPT or Gemini), mitigates the "entropy collapse" observed in prior work, and maintains stable training. Across diverse visual agentic tasks, GTR-Turbo improves the accuracy of the baseline model by 10-30% while reducing wall-clock training time by 50% and compute cost by 60% relative to GTR.

cs.CV↗

arXiv2026

Hi-Agent: Hierarchical Vision-Language Agents for Mobile Device Control

Building agents that autonomously operate mobile devices has attracted increasing attention. While Vision-Language Models (VLMs) show promise, most existing approaches rely on direct state-to-action mappings, which lack structured reasoning and planning, and thus generalize poorly to novel tasks or unseen UI layouts. We introduce Hi-Agent, a trainable hierarchical vision-language agent for mobile control, featuring a high-level reasoning model and a low-level action model that are jointly optimized. For efficient training, we reformulate multi-step decision-making as a sequence of single-step subgoals and propose a foresight advantage function, which leverages execution feedback from the low-level model to guide high-level optimization. This design alleviates the path explosion issue encountered by Group Relative Policy Optimization (GRPO) in long-horizon tasks and enables stable, critic-free joint training. Hi-Agent achieves a new State-Of-The-Art (SOTA) 87.9% task success rate on the Android-in-the-Wild (AitW) benchmark, significantly outperforming prior methods across three paradigms: prompt-based (AppAgent: 17.7%), supervised (Filtered BC: 54.5%), and reinforcement learning-based (DigiRL: 71.9%). It also demonstrates competitive zero-shot generalization on the ScreenSpot-v2 benchmark. On the more challenging AndroidWorld benchmark, Hi-Agent also scales effectively with larger backbones, showing strong adaptability in high-complexity mobile control scenarios.

cs.AI↗

arXiv2025

Decoupling Understanding from Reasoning via Problem Space Mapping for Small-Scale Model Reasoning

Despite recent advances in the reasoning capabilities of Large Language Models (LLMs), improving the reasoning ability of Small Language Models (SLMs, e.g., up to 1.5B parameters) remains challenging. A key obstacle lies in the complexity and variability of natural language: essentially equivalent problems often appear in diverse surface forms, often obscured by redundant or distracting details. This imposes a dual burden on SLMs: they must first extract the core problem from complex linguistic input, and then perform reasoning based on that understanding. The resulting vast and noisy problem space hinders optimization, particularly for models with limited capacity. To address this, we propose a new framework that decouples understanding from reasoning by mapping natural language problems into a canonical problem space-a semantically simplified yet expressive domain. This enables SLMs to focus on reasoning over standardized inputs, free from linguistic variability. Within this framework, we introduce DURIT (Decoupled Understanding from Reasoning via Iterative Training), a three-step algorithm that iteratively: (1) mapping natural language problems via reinforcement learning, (2) aligns reasoning trajectories through self-distillation, and (3) trains reasoning policies in the problem space. The mapper and reasoner are co-trained in an alternating loop throughout this process. Experiments show that DURIT substantially improves SLMs' performance on both in-domain and out-of-domain mathematical and logical reasoning tasks. Beyond improving reasoning capabilities, DURIT also improves the robustness of reasoning, validating decoupling understanding from reasoning as an effective strategy for strengthening SLMs.

cs.CL↗

arXiv2025

EndoSfM3D: Learning to 3D Reconstruct Any Endoscopic Surgery Scene using Self-supervised Foundation Model

3D reconstruction of endoscopic surgery scenes plays a vital role in enhancing scene perception, enabling AR visualization, and supporting context-aware decision-making in image-guided surgery. A critical yet challenging step in this process is the accurate estimation of the endoscope's intrinsic parameters. In real surgical settings, intrinsic calibration is hindered by sterility constraints and the use of specialized endoscopes with continuous zoom and telescope rotation. Most existing methods for endoscopic 3D reconstruction do not estimate intrinsic parameters, limiting their effectiveness for accurate and reliable reconstruction. In this paper, we integrate intrinsic parameter estimation into a self-supervised monocular depth estimation framework by adapting the Depth Anything V2 (DA2) model for joint depth, pose, and intrinsics prediction. We introduce an attention-based pose network and a Weight-Decomposed Low-Rank Adaptation (DoRA) strategy for efficient fine-tuning of DA2. Our method is validated on the SCARED and C3VD public datasets, demonstrating superior performance compared to recent state-of-the-art approaches in self-supervised monocular depth estimation and 3D reconstruction. Code and model weights can be found in project repository: https://github.com/MOYF-beta/EndoSfM3D.

cs.CV↗

arXiv2025

xMTF: A Formula-Free Model for Reinforcement-Learning-Based Multi-Task Fusion in Recommender Systems

Recommender systems need to optimize various types of user feedback, e.g., clicks, likes, and shares. A typical recommender system handling multiple types of feedback has two components: a multi-task learning (MTL) module, predicting feedback such as click-through rate and like rate; and a multi-task fusion (MTF) module, integrating these predictions into a single score for item ranking. MTF is essential for ensuring user satisfaction, as it directly influences recommendation outcomes. Recently, reinforcement learning (RL) has been applied to MTF tasks to improve long-term user satisfaction. However, existing RL-based MTF methods are formula-based methods, which only adjust limited coefficients within pre-defined formulas. The pre-defined formulas restrict the RL search space and become a bottleneck for MTF. To overcome this, we propose a formula-free MTF framework. We demonstrate that any suitable fusion function can be expressed as a composition of single-variable monotonic functions, as per the Sprecher Representation Theorem. Leveraging this, we introduce a novel learnable monotonic fusion cell (MFC) to replace pre-defined formulas. We call this new MFC-based model eXtreme MTF (xMTF). Furthermore, we employ a two-stage hybrid (TSH) learning strategy to train xMTF effectively. By expanding the MTF search space, xMTF outperforms existing methods in extensive offline and online experiments.

cs.IR↗

arXiv2024

GenCRF: Generative Clustering and Reformulation Framework for Enhanced Intent-Driven Information Retrieval

Query reformulation is a well-known problem in Information Retrieval (IR) aimed at enhancing single search successful completion rate by automatically modifying user's input query. Recent methods leverage Large Language Models (LLMs) to improve query reformulation, but often generate limited and redundant expansions, potentially constraining their effectiveness in capturing diverse intents. In this paper, we propose GenCRF: a Generative Clustering and Reformulation Framework to capture diverse intentions adaptively based on multiple differentiated, well-generated queries in the retrieval phase for the first time. GenCRF leverages LLMs to generate variable queries from the initial query using customized prompts, then clusters them into groups to distinctly represent diverse intents. Furthermore, the framework explores to combine diverse intents query with innovative weighted aggregation strategies to optimize retrieval performance and crucially integrates a novel Query Evaluation Rewarding Model (QERM) to refine the process through feedback loops. Empirical experiments on the BEIR benchmark demonstrate that GenCRF achieves state-of-the-art performance, surpassing previous query reformulation SOTAs by up to 12% on nDCG@10. These techniques can be adapted to various LLMs, significantly boosting retriever performance and advancing the field of Information Retrieval.

cs.IR↗

arXiv2020

Iterative Distance-Aware Similarity Matrix Convolution with Mutual-Supervised Point Elimination for Efficient Point Cloud Registration

In this paper, we propose a novel learning-based pipeline for partially overlapping 3D point cloud registration. The proposed model includes an iterative distance-aware similarity matrix convolution module to incorporate information from both the feature and Euclidean space into the pairwise point matching process. These convolution layers learn to match points based on joint information of the entire geometric features and Euclidean offset for each point pair, overcoming the disadvantage of matching by simply taking the inner product of feature vectors. Furthermore, a two-stage learnable point elimination technique is presented to improve computational efficiency and reduce false positive correspondence pairs. A novel mutual-supervision loss is proposed to train the model without extra annotations of keypoints. The pipeline can be easily integrated with both traditional (e.g. FPFH) and learning-based features. Experiments on partially overlapping and noisy point cloud registration show that our method outperforms the current state-of-the-art, while being more computationally efficient. Code is publicly available at https://github.com/jiahaowork/idam.

cs.CV↗