Entities · Locations
cs.CL
43 articles tagged with this entity.
-
PolyJarvis: An LLM-Orchestrated Agent for Automated All-Atom Molecular Dynamics of Amorphous Homopolymers
-
Efficient Decentralized Multi-task Dataset Valuation via Model Merging
-
CausalGame: Benchmarking Causal Thinking of LLM Agents in Games
-
Unified Audio Intelligence Without Regressing on Text Intelligence
-
Rethinking Speech-LLM Integration for ASR: Effective Joint Speech-Text Training by Interleaving
-
MultAttnAttrib: Training-Free Multimodal Attribution in Long Document Question Answering
-
Unlocking Speech-Text Compositional Powers: Instruction-Following Speech Language Models without Instruction Tuning
-
Are LLMs Reliable Rankers? Rank Manipulation via Two-Stage Token Optimization
-
How Far Do On-Prem Open LLMs Get on Text-to-SQL? A Cross-Family Size x Technique Frontier on BIRD
-
MultiHashFormer: Hash-based Generative Language Models
-
From Tokens to States: LLMs as a Special Case of World Models and the Continuous Path Beyond
-
Empowering GUI Agents via Autonomous Experience Exploration and Hindsight Experience Utilization for Task Planning
-
Context Recycling for Long-Horizon LLM Inference
-
Thinking Like a Scientist? A Structural Study of LLM-Generated Research Methods
-
Real-Time Voice AI Hears but Does Not Listen
-
Error-Aware TF-IDF Retrieval-Augmented Generation for ASR Error Correction
-
Improved Large Language Diffusion Models
-
Memory Makes the Difference: Evaluating How Different Memory Roles Shape Conversational Agents
-
Self-Recognition Finetuning can Prevent and Reverse Emergent Misalignment
-
CAVEWOMAN: How Large Language Models Behave Under Linguistic Input and Output Compression
-
FutureOmni: Evaluating Future Forecasting from Omni-Modal Context for Multimodal LLMs
-
MODE-RAG: Manifold Outlier Diagnosis and Energy-based Retrieval-Augmented Generation Evaluation
-
Think-at-Hard: Selective Latent Iterations to Improve Reasoning Language Models
-
Nemotron 3 Ultra: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning
-
Transfer Learning for FHIR Questionnaire Terminology Binding
-
Formalize Once, Edit the Rest: Efficient Lean-Based Answer Selection for Math Reasoning
-
Retrievable Gradients: Continual Post-Training Without Cumulative Weight Drift
-
PACT: Privileged Trace Co-Training for Multi-Turn Tool-Use Agents
-
DYNA : Dynamic Episodic Memory Networks for Augmenting Large Language Models with Temporal Knowledge Graphs in Continuous Learning
-
Fragile Knowledge, Robust Instruction-Following: The Width Pruning Dichotomy in Llama-3.2
-
Did You Forget What I Asked? Prospective Memory Failures in Large Language Models
-
MemRefine: LLM-Guided Compression for Long-Term Agent Memory
-
Scaling Self-Supervised Speech Models Uncovers Deep Linguistic Relationships: Evidence from the Pacific Cluster
-
Phantom transitions in language model fine-tuning
-
DIVERGE: Diversity-Enhanced RAG for Open-Ended Information Seeking
-
Mechanistic Data Attribution: Tracing the Training Origins of Interpretable LLM Units
-
Calibration of Structured Ignorance Certificates for Diagnosing Unknown Unknowns in Reasoning Models
-
Failure by Interference: Language Models Make Balanced Parentheses Errors When Faulty Mechanisms Overshadow Sound Ones
-
When Benign Inputs Lead to Severe Harms: Eliciting Unsafe Unintended Behaviors of Computer-Use Agents
-
"I understand your perspective": LLM Persuasion and Sycophancy through the Lens of Communicative Action Theory
-
Learning to Attack and Defend: Adaptive Red Teaming of Language Models via GRPO
-
Characterize Then Distill: Mechanistic Reasoning in Large Output Spaces
-
Re-Centering Humans in LLM Personalization