TPAMI 2026 papers on Large language models
23 of the 880 papers published in TPAMI 2026 (2.6%) are on Large language models, compared with 1.0% at TPAMI 2025. They fall into 7 topics.
See TPAMI 2026 in the interactive map
Working on something in this area? Describe your idea in scime atlas to see the closest papers by meaning and how crowded the spot has become.
Topics and papers
Instruction and fine-tuning · 5 papers
- Parameter-Efficient Fine-Tuning Methods for Pretrained Language Models: A Critical Review and Assessment (607 citations)
- LLM Post-Training: A Deep Dive Into Reasoning Large Language Models (231 citations)
- FiNE: Fine-Grained Neuron-Level Model Editing for Reliable and Safe LLMs (3 citations)
- LIFT+: Lightweight Fine-Tuning for Long-Tail Learning (3 citations)
- EVA: Editing for Versatile Alignment Against Jailbreaks (1 citation)
Language, safety and interpretability · 4 papers
- Jailbreak and Guard Aligned Language Models With Only Few In-Context Demonstrations (484 citations)
- Discrete Tokenization for Multimodal LLMs: A Comprehensive Survey (16 citations)
- OmniCharacter++: Toward Comprehensive Benchmark for Realistic Role-Playing Agents
- TraceRouter++: Causal Semantic Routing Realignment via Optimal Transport
Reasoning and chain of thought · 4 papers
- RBF++: Quantifying and Optimizing Reasoning Boundaries Across Measurable and Unmeasurable Capabilities for Chain-of-Thought Reasoning (8 citations)
- Audit-First Recombination for Test-Time LLM Optimization Under Deterministic Verifiers
- LLM Detoxification via Transition-Aware Reward-Guided Representation Sampling
- Efficient Inference for Large Reasoning Models: A Survey
Agents, code and math · 4 papers
- Abstracting Concept-Changing Rules for Solving Raven’s Progressive Matrix Problems (6 citations)
- InCLET: In-Context Learning Embeddings from LLM-Imagined Trajectories for Embodied Robot Instruction Following
- Industrial Brain: Self-Evolving Neuro-Symbolic Autonomy With Causal Resilience for Cyber-Physical Systems
- SymBOL: A General-Purpose Symbolic Learner for Scientific Discovery Using Bayesian Optimization-Enhanced Large Language Models
AI and society · 3 papers
- Survey of Computerized Adaptive Testing: A Machine Learning Perspective (66 citations)
- Aligning Perception, Reasoning, Modeling and Interaction: A Survey on Physical AI (15 citations)
- iPathWS: An Integrated Scalable System for Explainable Pathology Diagnosis With Spectral Heterogeneity Engine Networks
