We have 9 of 44 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
Both the quality loss from reuse and which repairs help depend on the LLM, even between two 8B models are introduced, as well as a common interface for adding new methods and an interactive leaderboard.
Fully Homomorphic Encryption (FHE) enables computation on encrypted data, preserving privacy throughout analysis. While its privacy is very strong, FHE is much slower to execute than the original computation. In particular, due to the recent success in accelerating its compute, the performance bottleneck shifts to the...
This work presents AgentServeSim, a simulator whose unit of execution is the agent program, and proposes LLM-driven automated agent-serving policy search using AgentServeSim as a CPU-based fitness evaluator.
Gated-Memory Routing is proposed, which conditions each decision on the query and a learned execution memory, and attains the best average accuracy, exceeding the strongest baseline by 2.44 points, while reducing HumanEval inference cost by 31.9% relative to that baseline.
This work analyzes SQD robustness on IBM Heron hardware across shot budgets, layouts, noise mitigation settings, and coupled-cluster singles and doubles amplitudes to identify where SQD provides genuine deployment robustness and where its limits remain.
CutBackdoor is presented, the first parameter-supply-chain backdoor that uses cut circuit execution from CutQC as the deployment-time trigger against VQAs, and poisoned parameters preserve full-circuit validation performance while substantially increasing cut-path reconstruction error under noisy finite-shot circuit-cu...
Noise-induced attacks that manipulate the Zero-Noise Extrapolation pipeline are the most damaging, followed by the QTrojan circuit-level backdoor, while the QDoor parameter-level backdoor is the least effective, yielding only marginal amplification.
LAMaS is a latency-aware orchestration framework for learning-based multi-agent systems that achieves the best latency among evaluated learning-based MAS baselines, reducing end-to-end latency by over 50% while maintaining competitive or better accuracy.
This work shows that a malicious developer can pair a benign-looking wrapper with crafted metadata to deterministically alter post-generation behavior without modifying model weights, training data, or inference backend, and introduces TIF-BAH, a lightweight middleware defense that verifies wrapper integrity and record...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
