4 citations · 7 across the 11 of their papers we have counts for
16 papers
SchemaFill: Efficient LLM Tool Calling via Slot-Parallel Speculative Decoding
Zhi-Kai Chen, Song-Yan Li, De-Chuan Zhan +1
LLM agents interact with external systems by generating structured tool calls. Given a user request, conversational context, and a catalog of tool schemas, a tool-calling model mus…
Consistent Plan-Act for Long-Horizon Agentic Tasks
Heng-Zhuang Li, Yi-Kai Zhang, Yu Wang +4
Long-horizon agentic tasks demand strong reasoning and efficient execution across successive interactions with dynamic environments. A common approach decouples high-level planning…
Routing Should Pay for Itself: Sparse Supervision for Economical LLM Routing
Guannan Lai, Gelin Bian, Hao-Xuan Ma +5
Large language model (LLM) routing reduces serving cost by assigning each query to an appropriate model while preserving response quality. Learning such a router, however, often re…
Token-Disentangled Latent Test-Time Scaling for Vision-Language Reasoning
Hao-Xuan Ma, Yihao Liu, Yutao Sun +8
Latent test-time scaling improves reasoning by refining hidden states during inference, but existing methods typically apply a single scalar reward to all editable latent tokens. F…
Bound State Analysis of Rank-One Delta Interactions Supported by Deformed Hyperspheres
Hilal Demirdöğen, Fatih Erman, Merve Nur Sayar
We study rank-one delta interactions supported by small normal deformations of an \(n\)-dimensional hypersphere \(S_R^n\subset\mathbb{R}^{n+1}\). The interaction is defined by the…
Dense Supervision, Sparse Updates: On the Sparsity and Geometry of On-Policy Distillation
Guo Yu, Wenlin Liu, Yulan Hu +3
On-policy distillation (OPD) has recently become a prominent post-training recipe by combining two desirable ingredients: on-policy student-generated trajectories and dense token-l…
CAST: Game Solvers as Turn-Level Teachers for LLM Agents
Yu Wang, Yi-Kai Zhang, Wentao Shi +8
Training large language models (LLMs) to act in long-horizon games is a promising step toward generalist decision-making, yet reinforcement learning with verifiable rewards (RLVR)…
: Generalist Value Model as a Prior for Sparse RL Rollouts
Yi-Kai Zhang, Yueqing Sun, Hongyan Hao +4
In Reinforcement Learning with Verifiable Rewards (RLVR), constructing a robust advantage baseline is critical for policy gradients, effectively guiding the policy model to reinfor…
Multimodal Tabular Reasoning with Privileged Structured Information
Jun-Peng Jiang, Yu Xia, Hai-Long Sun +6
Tabular reasoning involves multi-step information extraction and logical inference over tabular data. While recent advances have leveraged large language models (LLMs) for reasonin…
UniCA: Unified Covariate Adaptation for Time Series Foundation Model
Lu Han, Yu Liu, Lan Li +9
Time Series Foundation Models (TSFMs) have achieved remarkable success through large-scale pretraining. However, their design primarily targets real-valued series, limiting their a…
Mitigating Visual Forgetting via Take-along Visual Conditioning for Multi-modal Long CoT Reasoning
Hai-Long Sun, Zhun Sun, Houwen Peng +1
Recent advancements in Large Language Models (LLMs) have demonstrated enhanced reasoning capabilities, evolving from Chain-of-Thought (CoT) prompting to advanced, product-oriented…
OmniEvalKit: A Modular, Lightweight Toolbox for Evaluating Large Language Model and its Omni-Extensions
Yi-Kai Zhang, Xu-Xiang Zhong, Shiyin Lu +3
The rapid advancements in Large Language Models (LLMs) have significantly expanded their applications, ranging from multilingual support to domain-specific tasks and multimodal int…
MOS: Model Surgery for Pre-Trained Model-Based Class-Incremental Learning
Hai-Long Sun, Da-Wei Zhou, Hanbin Zhao +3
Class-Incremental Learning (CIL) requires models to continually acquire knowledge of new classes without forgetting old ones. Despite Pre-trained Models (PTMs) have shown excellent…
Ovis: Structural Embedding Alignment for Multimodal Large Language Model
Shiyin Lu, Yang Li, Qing-Guo Chen +4
Current Multimodal Large Language Models (MLLMs) typically integrate a pre-trained LLM with another pre-trained vision transformer through a connector, such as an MLP, endowing the…
Wings: Learning Multimodal LLMs without Text-only Forgetting
Yi-Kai Zhang, Shiyin Lu, Yang Li +7
Multimodal large language models (MLLMs), initiated with a trained LLM, first align images with text and then fine-tune on multimodal mixed inputs. However, the MLLM catastrophical…
Parrot: Multilingual Visual Instruction Tuning
Hai-Long Sun, Da-Wei Zhou, Yang Li +8
The rapid development of Multimodal Large Language Models (MLLMs), such as GPT-4o, marks a significant step toward artificial general intelligence. Existing methods typically align…