|
scholar.google.com
|
<i class="ai ai-google-scholar-square ai-2x"></i>
|
Анализировать url
|
|
linkedin.com
|
<i class="fab fa-linkedin ai-2x"></i>
<!-- <a href="personalstatement/ps.mp4">[A vedio of personal statement]</a> -->
|
Анализировать url
|
|
ece.queensu.ca
|
Department of Electrical and Computer Engineering
|
Анализировать url
|
|
queensu.ca
|
Queen's University
|
Анализировать url
|
|
eecs.pku.edu.cn
|
School of Electronics Engineering and Computer Science
|
Анализировать url
|
|
pku.edu.cn
|
Peking University
|
Анализировать url
|
|
github.com
|
here
|
Анализировать url
|
|
aclrollingreview.org
|
ACL Rolling Review
|
Анализировать url
|
|
scholar.google.com
|
Google Scholar Page
|
Анализировать url
|
|
openreview.net
|
Anchoring the Cache: Mitigating Contextual Hallucination in KV-Compressed Long-Context Summarization
|
Анализировать url
|
|
arxiv.org
|
To trust or not to trust: Attention-based Trust Management for LLM Multi-Agent Systems
|
Анализировать url
|
|
arxiv.org
|
Do VLMs Have a Moral Backbone? A Study on the Fragile Morality of Vision-Language Models
|
Анализировать url
|
|
openreview.net
|
Graph-Assisted Large Language Models: A Perspective on Mitigating Intrinsic Limitations
|
Анализировать url
|
|
openreview.net
|
A Reward-Guided Dual-Phase Framework for Adaptive Inference-Time Reasoning
|
Анализировать url
|
|
arxiv.org
|
MORALISE: A Structured Benchmark for Moral Alignment in Visual Language Models
|
Анализировать url
|
|
arxiv.org
|
From Seeing to Thinking: Decoupling Perception and Reasoning Improves Post-Training of Vision-Language Models
|
Анализировать url
|
|
arxiv.org
|
When Token Pruning is Worse than Random: Understanding Visual Token Information in VLLMs
|
Анализировать url
|
|
openreview.net
|
How Far Are LLMs from Professional Poker Players? Revisiting Game-Theoretic Reasoning with Agentic Tool Use
|
Анализировать url
|
|
arxiv.org
|
Seeing but Not Believing: Probing the Disconnect Between Visual Attention and Answer Correctness in VLMs
|
Анализировать url
|
|
arxiv.org
|
Bradley-Terry and Multi-Objective Reward Modeling Are Complementary
|
Анализировать url
|
|
arxiv.org
|
Unlocking the Power of Multi-Agent LLM for Reasoning: From Lazy Agents to Deliberation
|
Анализировать url
|
|
arxiv.org
|
TRAJECT-Bench:A Trajectory-Aware Benchmark for Evaluating Agentic Tool Use
|
Анализировать url
|
|
arxiv.org
|
Synthesizing High-Quality Visual Question Answering from Medical Documents with Generator-Verifier LMMs
|
Анализировать url
|
|
openreview.net
|
DiffKGW: Stealthy and Robust Diffusion Model Watermarking
|
Анализировать url
|
|
arxiv.org
|
Harnessing the Unseen: The Hidden Influence of Intrinsic Knowledge in Long-Context Language Models
|
Анализировать url
|
|
arxiv.org
|
SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language Models
|
Анализировать url
|
|
arxiv.org
|
AgentTTS: Large Language Model Agent for Test-time Compute-optimal Scaling Strategy in Complex Tasks
|
Анализировать url
|
|
arxiv.org
|
Keeping an Eye on LLM Unlearning: The Hidden Risk and Remedy
|
Анализировать url
|
|
arxiv.org
|
Efficient Long CoT Reasoning in Small Language Models
|
Анализировать url
|
|
arxiv.org
|
m1: Unleash the Potential of Test-Time Scaling for Medical Reasoning with Large Language Models
|
Анализировать url
|
|
arxiv.org
|
MedVLThinker: Simple Baselines for Multimodal Medical Reasoning
|
Анализировать url
|
|
arxiv.org
|
Does Multimodal Large Language Model Truly Unlearn? Stealthy MLLM Unlearning Attack
|
Анализировать url
|
|
arxiv.org
|
Beyond Text: Unveiling Privacy Vulnerabilities in Multi-modal Retrieval-Augmented Generation
|
Анализировать url
|
|
arxiv.org
|
ViLBench: A Suite for Vision-Language Process Reward Modeling
|
Анализировать url
|
|
openreview.net
|
Automatic Task-aware Instruction Optimizer for Black-box LLMs
|
Анализировать url
|
|
arxiv.org
|
EcomScriptBench: A Multi-task Benchmark for E-commerce Script Planning via Step-wise Intention-Driven Product Association
|
Анализировать url
|
|
arxiv.org
|
Stepwise Perplexity-Guided Refinement for Efficient Chain-of-Thought Reasoning in Large Language Models
|
Анализировать url
|
|
arxiv.org
|
Divide-Verify-Refine: Aligning LLM Responses with Complex Instructions
|
Анализировать url
|
|
arxiv.org
|
Reasoning with Graphs: Structuring Implicit Knowledge to Enhance LLMs Reasoning
|
Анализировать url
|
|
arxiv.org
|
A General Framework to Enhance Fine-tuning-based LLM Unlearning
|
Анализировать url
|
|
arxiv.org
|
Examples as the Prompt: A Scalable Approach for Efficient LLM Adaptation in E-Commerce
|
Анализировать url
|
|
openreview.net
|
Catastrophic Failure of LLM Unlearning via Quantization
|
Анализировать url
|
|
github.com
|
code
|
Анализировать url
|
|
news.ycombinator.com
|
Hacker News
|
Анализировать url
|
|
openreview.net
|
Unlocking Efficient, Scalable, and Continual Knowledge Editing with Basis-Level Representation Fine-Tuning
|
Анализировать url
|
|
aclanthology.org
|
SimRAG: Self-Improving Retrieval-Augmented Generation for Adapting Large Language Models to Specialized Domains
|
Анализировать url
|
|
aclanthology.org
|
Towards Knowledge Checking in Retrieval-augmented Generation: A Representation Perspective
|
Анализировать url
|
|
aclanthology.org
|
Learning with Less: Knowledge Distillation from Large Language Models via Unlabeled Data
|
Анализировать url
|
|
arxiv.org
|
Exploring Query Understanding for Amazon Product Search
|
Анализировать url
|
|
aclanthology.org
|
Knowledge-Selective Pretraining for Attribute Value Extraction
|
Анализировать url
|
|
ojs.aaai.org
|
Interpretable Low-Resource Legal Decision Making
|
Анализировать url
|
|
aclanthology.org
|
Unsupervised Conversation Disentanglement through Co-Training
|
Анализировать url
|
|
github.com
|
code
|
Анализировать url
|
|
aclanthology.org
|
Retrieval, Analogy, and Composition: A framework for Compositional Generalization in Image Captioning
|
Анализировать url
|
|
caiac.pubpub.org
|
Descriptive Image Captioning with Salient Retrieval Priors
|
Анализировать url
|
|
aclanthology.org
|
Enhancing Descriptive Image Captioning with Natural Language Inference
|
Анализировать url
|
|
github.com
|
code
|
Анализировать url
|
|
dl.acm.org
|
Partner Matters! An Empirical Study on Fusing Personas for Personalized Response Selection in Retrieval-Based Chatbots
|
Анализировать url
|
|
github.com
|
code
|
Анализировать url
|
|
aclweb.org
|
Improving Pretrained Models for Zero-shot Multi-label Text Classification through Reinforced Label Hierarchy Reasoning
|
Анализировать url
|
|
github.com
|
code
|
Анализировать url
|
|
ieeexplore.ieee.org
|
Have You Made A Decision? Where? A Pilot Study on Interpretability of Polarity Analysis Based on Advising Problem
|
Анализировать url
|
|
github.com
|
code
|
Анализировать url
|
|
ijcai.org
|
End-to-End Transition-Based Online Dialogue Disentanglement
|
Анализировать url
|
|
github.com
|
code
|
Анализировать url
|
|
aclweb.org
|
Towards Explainable NLP: A Generative Explanation Framework for Text Classification
|
Анализировать url
|
|
github.com
|
code
|
Анализировать url
|
|
dl.acm.org
|
QuoteRec: Toward Quote Recommendation for Writing
|
Анализировать url
|
|
arxiv.org
|
Attention Knows Whom to Trust: Attention-based Trust Management for LLM Multi-Agent Systems
|
Анализировать url
|
|
arxiv.org
|
Comprehensive Vulnerability Analysis is Necessary for Trustworthy LLM-MAS
|
Анализировать url
|
|
arxiv.org
|
Cite Before You Speak: Enhancing Context-Response Grounding in E-commerce Conversational LLM-Agents
|
Анализировать url
|
|
arxiv.org
|
How Far are LLMs from Real Search? A Comprehensive Study on Efficiency, Completeness, and Inherent Capabilities
|
Анализировать url
|
|
arxiv.org
|
A Survey of Calibration Process for Black-Box LLMs
|
Анализировать url
|
|
github.com
|
Ask Gemini
|
Анализировать url
|
|
en.wikipedia.org
|
Ji'an, China
|
Анализировать url
|