Learning Adaptive Reasoning Paths for Efficient Visual Reasoning
Paper • 2604.14568 • Published • 8
AI & ML interests
None defined yet.
Recent Activity
View all activity
DarthZhu
authored a
paper 14 days ago
yixuH
authored a
paper 17 days ago
DarthZhu
submitted a
paper to Daily Papers 17 days ago
Xiaogeng-Liu
authored 5
papers 3 months ago
InjecGuard: Benchmarking and Mitigating Over-defense in Prompt Injection Guardrail Models
Paper • 2410.22770 • Published
Doxing via the Lens: Revealing Privacy Leakage in Image Geolocation for Agentic Multi-Modal Large Reasoning Model
Paper • 2504.19373 • Published • 1
Code Agent can be an End-to-end System Hacker: Benchmarking Real-world Threats of Computer-use Agent
Paper • 2510.06607 • Published • 4
AutoDAN-Reasoning: Enhancing Strategies Exploration based Jailbreak Attacks with Test-Time Scaling
Paper • 2510.05379 • Published
ReasoningBomb: A Stealthy Denial-of-Service Attack by Inducing Pathologically Long Reasoning in Large Reasoning Models
Paper • 2602.00154 • Published
DarthZhu
authored a
paper 11 months ago
DarthZhu
authored 4
papers over 1 year ago
Deductive Beam Search: Decoding Deducible Rationale for Chain-of-Thought Reasoning
Paper • 2401.17686 • Published • 2
How Easily do Irrelevant Inputs Skew the Responses of Large Language Models?
Paper • 2404.03302 • Published • 2
From Persona to Personalization: A Survey on Role-Playing Language Agents
Paper • 2404.18231 • Published • 1
Unraveling Cross-Modality Knowledge Conflict in Large Vision-Language Models
Paper • 2410.03659 • Published • 5
Muhao
authored 7
papers almost 2 years ago
CLIMB: A Benchmark of Clinical Bias in Large Language Models
Paper • 2407.05250 • Published • 2
mDPO: Conditional Preference Optimization for Multimodal Large Language Models
Paper • 2406.11839 • Published • 40
Can NLI Provide Proper Indirect Supervision for Low-resource Biomedical Relation Extraction?
Paper • 2212.10784 • Published • 1
Instructions as Backdoors: Backdoor Vulnerabilities of Instruction Tuning for Large Language Models
Paper • 2305.14710 • Published • 3
UniversalNER: Targeted Distillation from Large Language Models for Open Named Entity Recognition
Paper • 2308.03279 • Published • 24
Software Entity Recognition with Noise-Robust Learning
Paper • 2308.10564 • Published • 1
PINTO: Faithful Language Reasoning Using Prompt-Generated Rationales
Paper • 2211.01562 • Published • 1