29 citations · 31 across the 21 of their papers we have counts for
23 papers
Instella-MoE Technical Report
Jiang Liu, Sudhanshu Ranjan, Prakamya Mishra +10
In this work, we introduce Instella-MoE, a fully open Mixture-of-Experts (MoE) language model with 16 billion total parameters and 2.8 billion active parameters per token, trained…
PR2: Predictive Routing Replay for MoE-Based LLM Reinforcement Learning
Daize Dong, Junlin Chen, Haolong Jia +9
Mixture of Experts (MoE) Large Language Models (LLMs) achieve strong performance at scale. However, reinforcement learning (RL) on MoE-based LLMs often suffers from training instab…
VideoSeek: Long-Horizon Video Agent with Tool-Guided Seeking
Jingyang Lin, Jialian Wu, Jiang Liu +6
Video agentic models have advanced challenging video-language tasks. However, most agentic approaches still heavily rely on greedy parsing over densely sampled video frames, result…
TermiGen: High-Fidelity Environment and Robust Trajectory Synthesis for Terminal Agents
Kaijie Zhu, Yuzhou Nie, Yijiang Li +10
Executing complex terminal tasks remains a significant challenge for open-weight LLMs, constrained by two fundamental limitations. First, high-fidelity, executable training environ…
Reliable Use of Lemmas via Eligibility Reasoning and SectionAware Reinforcement Learning
Zhikun Xu, Xiaodong Yu, Ben Zhou +6
Recent large language models (LLMs) perform strongly on mathematical benchmarks yet often misapply lemmas, importing conclusions without validating assumptions. We formalize lemma$…
CD4LM: Consistency Distillation and aDaptive Decoding for Diffusion Language Models
Yihao Liang, Ze Wang, Hao Chen +7
Autoregressive large language models achieve strong results on many benchmarks, but decoding remains fundamentally latency-limited by sequential dependence on previously generated…
XTrace: A Non-Invasive Dynamic Tracing Framework for Android Applications in Production
Qi Hu, Jiangchao Liu, Xin Yu +2
As the complexity of mobile applications grows exponentially and the fragmentation of user device environments intensifies, ensuring online application stability faces unprecedente…
Instella: Fully Open Language Models with Stellar Performance
Jiang Liu, Jialian Wu, Xiaodong Yu +10
Large language models (LLMs) have demonstrated remarkable performance across a wide range of tasks, yet the majority of high-performing models remain closed-source or partially ope…
Learning from Online Videos at Inference Time for Computer-Use Agents
Yujian Liu, Ze Wang, Hao Chen +7
Computer-use agents can operate computers and automate laborious tasks, but despite recent rapid progress, they still lag behind human users, especially when tasks require domain-s…
FarSkip-Collective: Unhobbling Blocking Communication in Mixture of Experts Models
Yonatan Dukler, Guihong Li, Deval Shah +3
Blocking communication presents a major hurdle in running MoEs efficiently in distributed settings. To address this, we present FarSkip-Collective which modifies the architecture o…
Latent Visual Reasoning
Bangzheng Li, Ximeng Sun, Jiang Liu +7
Multimodal Large Language Models (MLLMs) have achieved notable gains in various tasks by incorporating Chain-of-Thought (CoT) reasoning in language spaces. Recent work extends this…
XModBench: Benchmarking Cross-Modal Capabilities and Consistency in Omni-Language Models
Xingrui Wang, Jiang Liu, Chao Huang +7
Omni-modal large language models (OLLMs) aim to unify audio, vision, and text understanding within a single framework. While existing benchmarks primarily evaluate general cross-mo…
DRIFT: Transferring Reasoning Priors for Efficient MLLM Fine-Tuning
Chao Huang, Zeliang Zhang, Jiang Liu +7
Multimodal large language models (MLLMs) have made rapid progress, yet their reasoning ability often lags behind strong text-only LLMs. Bridging this gap typically requires large-s…
ImageDoctor: Diagnosing Text-to-Image Generation via Grounded Image Reasoning
Yuxiang Guo, Jiang Liu, Ze Wang +7
The rapid advancement of text-to-image (T2I) models has increased the need for reliable human preference modeling, a demand further amplified by recent progress in reinforcement le…
APRIL: Active Partial Rollouts in Reinforcement Learning to Tame Long-tail Generation
Yuzhen Zhou, Jiajun Li, Yusheng Su +15
Reinforcement learning (RL) has become a cornerstone in advancing large-scale pre-trained language models (LLMs). Successive generations, including GPT-o series, DeepSeek-R1, Kimi-…
Instella-T2I: Pushing the Limits of 1D Discrete Latent Space Image Generation
Ze Wang, Hao Chen, Benran Hu +7
Image tokenization plays a critical role in reducing the computational demands of modeling high-resolution images, significantly improving the efficiency of image and multimodal un…
TTT-Bench: A Benchmark for Evaluating Reasoning Ability with Simple and Novel Tic-Tac-Toe-style Games
Prakamya Mishra, Jiang Liu, Jialian Wu +3
Large reasoning models (LRMs) have demonstrated impressive reasoning capabilities across a broad range of tasks including Olympiad-level mathematical problems, indicating evidence…
Unleashing Hour-Scale Video Training for Long Video-Language Understanding
Jingyang Lin, Jialian Wu, Ximeng Sun +8
Recent long-form video-language understanding benchmarks have driven progress in video large multimodal models (Video-LMMs). However, the scarcity of well-annotated long videos has…
MOVi: Training-free Text-conditioned Multi-Object Video Generation
Aimon Rahman, Jiang Liu, Ze Wang +7
Recent advances in diffusion-based text-to-video (T2V) models have demonstrated remarkable progress, but these models still face challenges in generating videos with multiple objec…
KeyVID: Keyframe-Aware Video Diffusion for Audio-Synchronized Visual Animation
Xingrui Wang, Jiang Liu, Ze Wang +7
Generating video from various conditions, such as text, image, and audio, enables both spatial and temporal control, leading to high-quality generation results. Videos with dramati…
Self-Taught Agentic Long Context Understanding
Yufan Zhuang, Xiaodong Yu, Jialian Wu +7
Answering complex, long-context questions remains a major challenge for large language models (LLMs) as it requires effective question clarifications and context retrieval. We prop…
Agent Laboratory: Using LLM Agents as Research Assistants
Samuel Schmidgall, Yusheng Su, Ze Wang +7
Historically, scientific discovery has been a lengthy and costly process, demanding substantial time and resources from initial conception to final results. To accelerate scientifi…
SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer
Hao Chen, Ze Wang, Xiang Li +7
Efficient image tokenization with high compression ratios remains a critical challenge for training generative models. We present SoftVQ-VAE, a continuous image tokenizer that leve…