Computation and Language

Uncertainty Quantification for LLMs through Minimum Bayes Risk: Bridging Confidence and Consistency

Uncertainty Quantification for LLMs through Mi...

Computation and Language
Avatar
Екатерина Трюх
106 views
SciDiagramEdit: Learning to Edit Scientific Diagrams from Paper Revisions

SciDiagramEdit: Learning to Edit Scientific Di...

Computation and Language
Avatar
librarian
148 views
T^2MLR: Transformer with Temporal Middle-Layer Recurrence

T^2MLR: Transformer with Temporal Middle-Layer...

Computation and Language
Avatar
Ziyang Cai
141 views
WebSwarm: Recursive Multi-Agent Orchestration for Deep-and-Wide Web Search

WebSwarm: Recursive Multi-Agent Orchestration ...

Computation and Language
Avatar
Xiaoshuai Song
157 views
Reinforcement Learning with Metacognitive Feedback Elicits Faithful Uncertainty Expression in LLMs

Reinforcement Learning with Metacognitive Feed...

Computation and Language
Avatar
librarian
160 views
Why Multi-Step Tool-Use Reinforcement Learning Collapses and How Supervisory Signals Fix It

Why Multi-Step Tool-Use Reinforcement Learning...

Computation and Language
Avatar
abcdezzy688
171 views
Staying In Character: Perspective-Bounded Memory For Book-Based Role-Playing Agents

Staying In Character: Perspective-Bounded Memo...

Computation and Language
Avatar
Xushuo Tang
162 views
Toward Generalist Autonomous Research via Hypothesis-Tree Refinement

Toward Generalist Autonomous Research via Hypo...

Computation and Language
Avatar
Jiajie Jin
200 views
End-to-End Context Compression at Scale

End-to-End Context Compression at Scale

Computation and Language
Avatar
librarian
181 views
SPADE-Bench: Evaluating Spontaneous Strategic Deception in Agents via Plan-Action Divergence

SPADE-Bench: Evaluating Spontaneous Strategic ...

Computation and Language
Avatar
librarian
195 views
Rethinking Memory as Continuously Evolving Connectivity

Rethinking Memory as Continuously Evolving Con...

Computation and Language
Avatar
librarian
207 views
MeMo: Memory as a Model

MeMo: Memory as a Model

Computation and Language
Avatar
Ryan Quek
251 views
The Impossibility Triangle of Long-Context Modeling

The Impossibility Triangle of Long-Context Mod...

Computation and Language
Avatar
librarian
224 views
GiVA: Gradient-Informed Bases for Vector-Based Adaptation

GiVA: Gradient-Informed Bases for Vector-Based...

Computation and Language
Avatar
Neeraj Gangwar
234 views
A Multimodal Text- and Graph-Based Approach for Open-Domain Event Extraction from Documents

A Multimodal Text- and Graph-Based Approach fo...

Computation and Language
Avatar
librarian
254 views
Chat2Workflow: A Benchmark for Generating Executable Visual Workflows with Natural Language

Chat2Workflow: A Benchmark for Generating Exec...

Computation and Language
Avatar
librarian
232 views
CD2CR: Co-reference Resolution Across Documents and Domains

CD2CR: Co-reference Resolution Across Document...

Computation and Language
Avatar
k-m-smit2
240 views
Demystifying OPD: Length Inflation and Stabilization Strategies for Large Language Models

Demystifying OPD: Length Inflation and Stabili...

Computation and Language
Avatar
librarian
306 views
ClawBench: Can AI Agents Complete Everyday Online Tasks?

ClawBench: Can AI Agents Complete Everyday Onl...

Computation and Language
Avatar
librarian
300 views
Synthetic Sandbox for Training Machine Learning Engineering Agents

Synthetic Sandbox for Training Machine Learnin...

Computation and Language
Avatar
Yuhang Zhou
295 views
Grounded Token Initialization for New Vocabulary in LMs for Generative Recommendation

Grounded Token Initialization for New Vocabula...

Computation and Language
Avatar
Daiwei Chen
310 views
AstroConcepts: A Large-Scale Multi-Label Classification Corpus for Astrophysics

AstroConcepts: A Large-Scale Multi-Label Class...

Computation and Language
Avatar
librarian
235 views
AgentSwing: Adaptive Parallel Context Management Routing for Long-Horizon Web Agents

AgentSwing: Adaptive Parallel Context Manageme...

Computation and Language
Avatar
librarian
286 views
F2LLM-v2: Inclusive, Performant, and Efficient Embeddings for a Multilingual World

F2LLM-v2: Inclusive, Performant, and Efficient...

Computation and Language
Avatar
librarian
408 views
Nemotron-Cascade 2: Post-Training LLMs with Cascade RL and Multi-Domain On-Policy Distillation

Nemotron-Cascade 2: Post-Training LLMs with Ca...

Computation and Language
Avatar
librarian
337 views
Learning When to Attend: Conditional Memory Access for Long-Context LLMs

Learning When to Attend: Conditional Memory Ac...

Computation and Language
Avatar
Aditya Chattopadhyay
314 views
Knowledge Distillation with Structured Chain-of-Thought for Text-to-SQL

Knowledge Distillation with Structured Chain-o...

Computation and Language
Avatar
Khushboo Thaker
269 views
SciMDR: Benchmarking and Advancing Scientific Multimodal Document Reasoning

SciMDR: Benchmarking and Advancing Scientific ...

Computation and Language
Avatar
librarian
295 views
Instruction set for the representation of graphs

Instruction set for the representation of graphs

Computation and Language
Avatar
Ezequiel López-Rubio
268 views
Monitoring Emergent Reward Hacking During Generation via Internal Activations

Monitoring Emergent Reward Hacking During Gene...

Computation and Language
Avatar
librarian
273 views
CHIMERA: Compact Synthetic Data for Generalizable LLM Reasoning

CHIMERA: Compact Synthetic Data for Generaliza...

Computation and Language
Avatar
Xinyu Zhu
282 views
Team of Thoughts: Efficient Test-time Scaling of Agentic Systems through Orchestrated Tool Calling

Team of Thoughts: Efficient Test-time Scaling ...

Computation and Language
Avatar
librarian
306 views
Load more