4 citations · 7 across the 25 of their papers we have counts for
16 papers · 1 filter
Asynchronous Fast-Slow Vision-Language-Action Policies for Whole-Body Robotic Manipulation
Teqiang Zou, Hongliang Zeng, Yuxuan Nong +6
Most Vision-Language-Action (VLA) systems integrate a Vision-Language Model (VLM) for semantic reasoning with an action expert generating continuous action signals, yet both typica…
Evaluating Large Language Models on Multimodal Chemistry Olympiad Exams
Yiming Cui, Xin Yao, Yuxuan Qin +3
Multimodal scientific reasoning remains a significant challenge for large language models (LLMs), particularly in chemistry, where problem-solving relies on symbolic diagrams, mole…
The Urysohn Ladder: Recursive Metric Contraction for Scalable Continual Learning
Xin Li
Continual learning systems face a fundamental geometric obstacle: as experience accumulates on a fixed-capacity manifold, covering numbers grow linearly with time, eventually forci…
The Homological Brain: Parity Principle and Amortized Inference
Xin Li
Biological intelligence emerges from substrates that are slow, noisy, and energetically constrained, yet it performs rapid and coherent inference in open-ended environments. Classi…
Poincaré Meets Bellman: Revisable Memory, Operational Quotients, and Evidence-Supported Learning in Changing Environments
Xin Li
Memory consolidation determines both what a learner can do now and which changes remain implementable later. We develop a finite-model synthesis of operational state abstraction an…
The Geometry of Certainty: Recursive Topological Condensation and the Limits of Inference
Xin Li
Computation fundamentally separates time from space: nondeterministic search is exponential in time but polynomially simulable in space (Savitch's Theorem). We propose that the bra…
InfoAgent: Advancing Autonomous Information-Seeking Agents
Gongrui Zhang, Jialiang Zhu, Ruiqi Yang +15
Building Large Language Model agents that expand their capabilities by interacting with external tools represents a new frontier in AI research and applications. In this paper, we…
Cycle is All You Need: More Is Different
Xin Li
We propose an information-topological framework in which cycle closure is the fundamental mechanism of memory and consciousness. Memory is not a static store but the ability to re-…
The Urysohn Machine: A Metric-Topological Model of Computation
Xin Li
We introduce the Urysohn Machine, an effective model of classification-oriented computation in which metric separation, frontier structure, and contraction are explicit parts of th…
What should we forget? A computational model of memory consolidation
Xin Li
Neural and immune memory rely on different biological mechanisms but face the same computational problem: future situations rarely repeat past ones exactly. Memory must retain dist…
Associative Memory for Non-Stationary Environments: A Self-Sizing Generalization of Hopfield Networks
Xin Li
The Hopfield network made associative memory (AM) the model system of neural computation, but it solves the problem only for a \emph{stationary} world: a fixed set of memories, sto…
Persistent Homology as a Theory of Emergent Structure
Xin Li
Why do some macroscopic structures remain identifiable even though their microscopic constituents continually change? Vortices persist while fluid parcels turn over, neural memorie…
Structural Decoupling: A Scaffold-Flow Theory of Generalization and Alignment
Xin Li
Learning in non-stationary and multi-context environments requires more than ordinary within-task generalization. A system must also discover which contexts exist, route inputs to…
From Large to Super-Tiny: End-to-End Optimization for Cost-Efficient LLMs
Jiliang Ni, Jiachen Pu, Zhongyi Yang +7
Large Language Models (LLMs) have significantly advanced artificial intelligence by optimizing traditional Natural Language Processing (NLP) workflows, facilitating their integrati…
A Survey on Enhancing Causal Reasoning Ability of Large Language Models
Xin Li, Zhuo Cai, Shoujin Wang +2
Large language models (LLMs) have recently shown remarkable performance in language tasks and beyond. However, due to their limited inherent causal reasoning ability, LLMs still fa…
RAPID: Long-Context Inference with Retrieval-Augmented Speculative Decoding
Guanzheng Chen, Qilong Feng, Jinjie Ni +2
The emergence of long-context large language models (LLMs) offers a promising alternative to traditional retrieval-augmented generation (RAG) for processing extensive documents. Ho…