1 citations · 3 across the 21 of their papers we have counts for
21 papers
NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness
NeoHorse Team, Guoliang Cao, Guohao Dai +34
Recursive self-improvement (RSI) requires a concrete mechanism through which an AI system observes its capabilities and converts that evidence into the next round of learning. We p…
Convolution for Large Language Models
Yuchuan Tian, Yingte Shu, Wei He +7
Large language models (LLMs) largely rely on Transformers, where self-attention provides global token interaction but does not explicitly encode the locality of natural language. W…
Agentic Routing: The Harness-Native Data Flywheel
Xinchen Liu, Hang Zhou, Yingjie Zong +12
Large language model agents are increasingly executed not by a single model call, but by an execution harness that manages observation, context, control, action, state, and verific…
SafeClawBench: Separating Semantic, Audit-Evidence, and Sandbox Harm in Tool-Using LLM Agents
Yuchuan Tian, Mengyu Zheng, Haocheng Mei +5
Tool-using language-model agents introduce security failures that go beyond unsafe text: they can disclose protected objects, write persistent memory, send messages, modify databas…
Claw-SWE-Bench: A Benchmark for Evaluating OpenClaw-style Agent Harnesses on Coding Tasks
Mengyu Zheng, Kai Han, Boxun Li +13
The software engineering capabilities of general-purpose agent harnesses remain underexplored, and existing benchmarks offer limited support for comparing these harnesses under con…
DLLM Agent: See Farther, Run Faster
Huiling Zhen, Weizhe Lin, Renxi Liu +15
Diffusion large language models (DLLMs) have emerged as an alternative to autoregressive (AR) decoding with appealing efficiency and modeling properties, yet their implications for…
From Next-Token to Next-Block: A Principled Adaptation Path for Diffusion LLMs
Yuchuan Tian, Yuchen Liang, Shuo Zhang +10
Diffusion Language Models (DLMs) enable fast generation, yet training large DLMs from scratch is costly. As a practical shortcut, adapting off-the-shelf Auto-Regressive (AR) model…
Top 10 Open Challenges Steering the Future of Diffusion Language Model and Its Variants
Yunhe Wang, Kai Han, Huiling Zhen +13
The paradigm of Large Language Models (LLMs) is currently defined by auto-regressive (AR) architectures, which generate text through a sequential ``brick-by-brick'' process. Despit…
Deferred Commitment Decoding for Diffusion Language Models
Yingte Shu, Yuchuan Tian, Chao Xu +2
Diffusion language models (DLMs) have recently emerged as a strong alternative to autoregressive models by enabling parallel text generation. To improve inference efficiency and KV…
Nexus: Higher-Order Attention Mechanisms in Transformers
Hanting Chen, Chong Zhu, Kai Han +6
Transformers have achieved significant success across various domains, relying on self-attention to capture dependencies. However, the standard first-order attention mechanism is o…
Revealing the Temporally Stable Bimodal Energy Distribution of FRB 20121102A with a Tripled Burst Set from AI Detections
Yidan Wang, Jing Han, Pei Wang +34
Active repeating Fast Radio Bursts (FRBs), with their large number of bursts, burst energy distribution, and their potential energy evolution, offer critical insights into the FRBs…
Circle-RoPE: Cone-like Decoupled Rotary Positional Embedding for Large Vision-Language Models
Chengcheng Wang, Jianyuan Guo, Hongguang Li +4
Rotary Position Embedding (RoPE) is widely adopted in large language models, but when applied to vision-language models (VLMs) it couples text and image position indices and can in…
Post-Training Quantization for Diffusion Transformer via Hierarchical Timestep Grouping
Ning Ding, Jing Han, Yuchuan Tian +3
Diffusion Transformer (DiT) has now become the preferred choice for building image generation models due to its great generation capability. Unlike previous convolution-based UNet…
U-REPA: Aligning Diffusion U-Nets to ViTs
Yuchuan Tian, Hanting Chen, Mengyu Zheng +3
Representation Alignment (REPA) that aligns Diffusion Transformer (DiT) hidden-states with ViT visual encoders has proven highly effective in DiT training, demonstrating superior c…
DiC: Rethinking Conv3x3 Designs in Diffusion Models
Yuchuan Tian, Jing Han, Chengcheng Wang +3
Diffusion models have shown exceptional performance in visual generation tasks. Recently, these models have shifted from traditional U-Shaped CNN-Attention hybrid structures to ful…
Learning Quantized Adaptive Conditions for Diffusion Models
Yuchen Liang, Yuchuan Tian, Lei Yu +4
The curvature of ODE trajectories in diffusion models hinders their ability to generate high-quality images in a few number of function evaluations (NFE). In this paper, we propose…
Instruct-IPT: All-in-One Image Processing Transformer via Weight Modulation
Yuchuan Tian, Jianhong Han, Hanting Chen +5
Due to the unaffordable size and intensive computation costs of low-level vision models, All-in-One models that are designed to address a handful of low-level vision tasks simultan…
U-DiTs: Downsample Tokens in U-Shaped Diffusion Transformers
Yuchuan Tian, Zhijun Tu, Hanting Chen +3
Diffusion Transformers (DiTs) introduce the transformer architecture to diffusion tasks for latent-space image generation. With an isotropic architecture that chains a series of tr…
DiJiang: Efficient Large Language Models through Compact Kernelization
Hanting Chen, Zhicheng Liu, Xutao Wang +2
In an effort to reduce the computational load of Transformers, research on linear attention has gained significant momentum. However, the improvement strategies for attention mecha…
PanGu- Pro:Rethinking Optimization and Architecture for Tiny Language Models
Yehui Tang, Kai Han, Fangcheng Liu +7
The power of large language models (LLMs) has been demonstrated through numerous data and computing resources. However, the application of language models on mobile devices is faci…
Towards Higher Ranks via Adversarial Weight Pruning
Yuchuan Tian, Hanting Chen, Tianyu Guo +2
Convolutional Neural Networks (CNNs) are hard to deploy on edge devices due to its high computation and storage complexities. As a common practice for model compression, network pr…