1 citations · 1 across the 15 of their papers we have counts for
17 papers
this-that-model-1.0: A typed decision model that decides in 30 ms, for a millionth of a cent
Zehua Cheng, Wei Dai, Jiahao Sun
Software delegates more of its branches to models every year: which queue a ticket enters, whether a command is safe to run, whether a claim clears without a person. What the progr…
Euston: Training Away Mathematical Sycophancy Without Losing the Mathematics
Zehua Cheng, Wei Dai, Jiahao Sun
Reasoning language models are trained to produce solutions, not to refuse them, and this bias persists when the problem they are handed is false. Asked to prove a corrupted theorem…
Constraint-Anchored Reasoning Traces
Zehua Cheng, Wei Dai, Jiahao Sun
Autoregressive multimodal large language models (MLLMs) suffer from error snowballing: a single incorrect inference early in a chainof-thought (CoT) trace corrupts all downstream r…
Equivariant Neural Belief Propagation
Zehua Cheng, Wei Dai, Jiahao Sun
Probabilistic inference over spatially embedded variables requires beliefs that respect symmetry, yet existing equivariant networks produce only scalars and vectors -- not…
In-Context Graphical Inference
Zehua Cheng, Wei Dai, Jiahao Sun
Marginal inference in discrete graphical models forces a choice between exactness and scalability: exact algorithms are intractable for high-treewidth graphs, while iterative appro…
Imbuing Large Language Models with Bidirectional Logic for Robust Chain Repair
Zehua Cheng, Wei Dai, Jiahao Sun +1
Autoregressive chain-of-thought (CoT) reasoning in large language models (LLMs) is fundamentally forward-directed: each step conditions only on prior tokens. This unidirectional in…
Invariant Gradient Alignment for Robust Reasoning Distillation
Zehua Cheng, Wei Dai, Jiahao Sun
Large language models (LLMs) suffer from shortcut learning: they systematically fail on out-of-distribution (OOD) inputs whose semantic surface differs from training data, even whe…
CasualSynth: Generating Structurally Sound Synthetic Data
Zehua Cheng, Wei Dai, Jiahao Sun +1
Large Language Models (LLMs) generate realistic synthetic data but offer no guarantee that their outputs respect the causal mechanisms governing the target domain. We introduce Cau…
Differentially Private Motif-Preserving Multi-modal Hashing
Zehua Cheng, Wei Dai, Jiahao Sun
Cross-modal hashing enables efficient retrieval by encoding images and text into compact binary codes. State-of-the-art methods rely on semantic similarity graphs derived from user…
Identity-Decoupled Anonymization for Visual Evidence in Multi-modal Retrieval-Augmented Generation
Zehua Cheng, Wei Dai, Jiahao Sun
Multi-modal retrieval-augmented generation (MRAG) systems retrieve visual evidence from large image corpora to ground the responses of large multi-modal models, yet the retrieved i…
CircuitSynth: Reliable Synthetic Data Generation
Zehua Cheng, Wei Dai, Jiahao Sun +1
The generation of high-fidelity synthetic data is a cornerstone of modern machine learning, yet Large Language Models (LLMs) frequently suffer from hallucinations, logical inconsis…
Constrained Policy Optimization for Provably Fair Order Matching
Zehua Cheng, Zhipeng Wang, Wei Dai +5
Automated matching engines execute millions of orders per session, yet systematic asymmetries in latency, order size, and market access compound into persistent execution dispariti…
Visual Set Program Synthesizer
Zehua Cheng, Wei Dai, Wenhu Zhang +2
A user pointing their phone at a supermarket shelf and asking "Which soda has the least sugar?" poses a difficult challenge for current visual Al assistants. Such queries require n…
Provable Defense Framework for LLM Jailbreaks via Noise-Augumented Alignment
Zehua Cheng, Jianwei Yang, Wei Dai +1
Large Language Models (LLMs) remain vulnerable to adaptive jailbreaks that easily bypass empirical defenses like GCG. We propose a framework for certifiable robustness that shifts…
A Control Theoretic Approach to Decentralized AI Economy Stabilization via Dynamic Buyback-and-Burn Mechanisms
Zehua Cheng, Wei Dai, Zhipeng Wang +3
The democratization of artificial intelligence through decentralized networks represents a paradigm shift in computational provisioning, yet the long-term viability of these ecosys…
Scaling Decentralized Learning with FLock
Zehua Cheng, Rui Sun, Jiahao Sun +1
Fine-tuning the large language models (LLMs) are prevented by the deficiency of centralized control and the massive computing and communication overhead on the decentralized scheme…
SoccerNet 2024 Challenges Results
Anthony Cioppa, Silvio Giancola, Vladimir Somers +81
The SoccerNet 2024 challenges represent the fourth annual video understanding challenges organized by the SoccerNet team. These challenges aim to advance research across multiple t…