Search Results for author:
Found 11 papers, 8 papers with code
InfiniteICL: Breaking the Limit of Context Window Size via Long Short-term Memory Transformation
In-context learning (ICL) is critical for large language models (LLMs), but its effectiveness is constrained by finite context windows, particularly in ultra-long contexts.
Beyond Intermediate States: Explaining Visual Redundancy through Language
Multi-modal Large Langue Models (MLLMs) often process thousands of visual tokens, which consume a significant portion of the context window and impose a substantial computational burden.
On the Transformations across Reward Model, Parameter Update, and In-Context Prompt
Despite the general capabilities of pre-trained large language models (LLMs), they still need further adaptation to better serve practical applications.
On the Worst Prompt Performance of Large Language Models
To address these limitations, we introduce RobustAlpacaEval, a new benchmark that consists of semantically equivalent case-level queries and emphasizes the importance of using the worst prompt performance to gauge the lower bound of model performance.
Pensieve: Retrospect-then-Compare Mitigates Visual Hallucination
Multi-modal Large Language Models (MLLMs) demonstrate remarkable success across various vision-language tasks.
Retrieval is Accurate Generation
To address this, we propose to initialize the training oracles using linguistic heuristics and, more importantly, bootstrap the oracles through iterative self-reinforcement.
ML-LMCL: Mutual Learning and Large-Margin Contrastive Learning for Improving ASR Robustness in Spoken Language Understanding
Specifically, in fine-tuning, we apply mutual learning and train two SLU models on the manual transcripts and the ASR transcripts, respectively, aiming to iteratively share knowledge between these two models.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
Alleviating Over-smoothing for Unsupervised Sentence Representation
Currently, learning better unsupervised sentence representations is the pursuit of many natural language processing communities.
FTM: A Frame-level Timeline Modeling Method for Temporal Graph Representation Learning
Existing neighborhood aggregation strategies fail to capture either the short-term features or the long-term features of temporal graph attributes, leading to unsatisfactory model performance and even poor robustness and domain generality of the representation learning method.
FiTs: Fine-grained Two-stage Training for Knowledge-aware Question Answering
Despite the promising result of recent KAQA systems which tend to integrate linguistic knowledge from pre-trained language models (PLM) and factual knowledge from knowledge graphs (KG) to answer complex questions, a bottleneck exists in effectively fusing the representations from PLMs and KGs because of (i) the semantic and distributional gaps between them, and (ii) the difficulties in joint reasoning over the provided knowledge from both modalities.
Bias-based Universal Adversarial Patch Attack for Automatic Check-out
To address the problem, this paper proposes a bias-based framework to generate class-agnostic universal adversarial patches with strong generalization ability, which exploits both the perceptual and semantic bias of models.
