Testing Whether Cemiplimab (REGN2810) Plus CDX-1140 Given Prior to Surgery Are Better Than Cemiplimab (REGN2810) Alone in Patients With Stage III-IV Head and Neck Cancer

Inclusion Criteria:

* Patients must have histologically or cytologically confirmed American Joint Committee on Cancer (AJCC) stage III-IV T0-4, N0-3b, M0 mucosal head and neck squamous cell carcinoma (HNSCC) (oral cavity, oropharynx, larynx, hypopharynx, and nasal cavity) that is appropriate for surgical resection. Both previously untreated (primary) and recurrent (salvage) settings will be eligible. Tumors must be accessible to biopsy in clinic (patients with laryngeal, hypopharyngeal, nasal cavity and base of tongue tumors will have endoscopic biopsies)
* For patients with oropharyngeal cancer, only p16-negative (non-human papillomavirus \[HPV\] related) patients will be eligible
* Patients must have measurable disease, defined as at least one lesion that can be accurately measured in at least one dimension (longest diameter to be recorded for non-nodal lesions and short axis for nodal lesions) as ≥ 20 mm (≥ 2 cm) by chest x-ray or as ≥ 10 mm (≥ 1 cm) with CT scan, MRI, or calipers by clinical exam
* Age ≥ 18 years. Because no dosing or adverse event (AE) data are currently available on the use of cemiplimab (REGN2810) alone or in combination with CDX-1140 in patients \< 18 years of age, children are excluded from this study
* Eastern Cooperative Oncology Group (ECOG) performance status ≤ 2 (Karnofsky ≥ 60%)
* Hemoglobin (Hb) ≥ 7 g/dL (transfusion allowed to bring Hb to this level)
* Absolute neutrophil count ≥ 1,000/mcL
* Platelets ≥ 100,000/mcL
* Total bilirubin ≤ 1.5 × institutional upper limit of normal (ULN)
* Aspartate aminotransferase (AST) (serum glutamic oxaloacetic transaminase \[SGOT\]) /alanine aminotransferase (ALT) (serum glutamic pyruvic transaminase \[SGPT\]) ≤ 3 × institutional ULN
* Creatinine ≤ 1.5 × institutional ULN OR glomerular filtration rate (GFR) ≥ 60 mL/min/1.73 m\^2
* Human immunodeficiency virus (HIV)-infected patients on effective anti-retroviral therapy with undetectable viral load within 6 months are eligible for this trial
* For patients with evidence of chronic hepatitis B virus (HBV) infection, the HBV viral load must be undetectable on suppressive therapy, if indicated
* Patients with a history of hepatitis C virus (HCV) infection must have been treated and cured. For patients with HCV infection who are currently on treatment, they are eligible if they have an undetectable HCV viral load
* Patients with known history or current symptoms of cardiac disease, or history of treatment with cardiotoxic agents, should have a clinical risk assessment of cardiac function using the New York Heart Association Functional Classification. To be eligible for this trial, patients should be class II or better
* Based on its mechanism of action, cemiplimab (REGN2810) can cause fetal harm when administered to a pregnant woman. Animal studies have demonstrated that inhibition of the PD-1/PD-L1 pathway can lead to increased risk of immune-mediated rejection of the developing fetus resulting in fetal death. Women of childbearing potential and men should use effective contraception during treatment with cemiplimab (REGN2810) and for 4 months after the last dose. The reproductive and developmental toxicity of CDX-1140 has not been evaluated. Women of childbearing potential and their partners who receive CDX-1140 must therefore take adequate contraceptive measures
* Ability to understand and the willingness to sign a written informed consent document. Legally authorized representatives may sign and give informed consent on behalf of study participants

Exclusion Criteria:

* Active or documented history of autoimmune disease within 2 years before screening
* Prior or planned allogeneic hematopoietic stem cell transplantation (HSCT)
* History of organ transplant that requires use of immunosuppressive medications
* Current or prior use of immunosuppressive medication within 14 days prior to the start of study drug administration. Immunosuppressants may interfere with study drug efficacy
* Any previous treatment with a PD-1 or PD-L1 inhibitor, including cemiplimab (REGN2810). It is unclear how prior exposure to immunotherapy would impact future use of checkpoint inhibitors
* Concurrent use of prednisone (10 mg or more)
* Patients with new pulmonary infiltrates indicative of pneumonitis, history of (non-infectious) pneumonitis/interstitial lung disease, or current pneumonitis/interstitial lung disease, including grade 1 pneumonitis (i.e., asymptomatic, clinical or diagnostic observation only, intervention not indicated)
* Another active malignancy for which the natural history or treatment has potential to interfere with the safety or efficacy assessment of the investigational regimen on this trial
* Patients who have not recovered from AE due to prior anti-cancer therapy (i.e., have residual toxicities \> grade 1) with the exception of alopecia
* Patients who are receiving any other investigational agents, such as concurrent chemotherapy, biologic, immunologic or hormonal therapy for cancer treatment
* History of allergic reactions attributed to compounds of similar chemical or biologic composition to CDX-1140 or cemiplimab (REGN2810)
* Patients with uncontrolled intercurrent illness or any other significant condition(s) that would make participation in this protocol unreasonably hazardous
* Pregnant women are excluded from this study because of the increased risk of immune-mediated rejection of the developing fetus with cemiplimab (REGN2810). Because of the potential for serious adverse reactions in breastfed children, women should not breastfeed during treatment with cemiplimab (REGN2810) and for at least 4 months after the last dose. These risks may also apply to CDX-1140